<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"
        xmlns:image="http://www.google.com/schemas/sitemap-image/1.1"
        xmlns:news="http://www.google.com/schemas/sitemap-news/0.9">
  <url>
    <loc>https://vybecoding.ai/news/anthropic-doubles-claude-code-rate-limits-spacex</loc>
    <lastmod>2026-05-18T22:20:39.799Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/88189763-ed89-442a-8957-590eb1887cd7</image:loc>
      <image:title>Anthropic Doubles Claude Code Rate Limits — Here's What Changed and Why SpaceX Made It Possible</image:title>
      <image:caption>Anthropic announced on May 6, 2026 at its Code with Claude developer conference in San Francisco that it is doubling Claude Code's five-hour rate limits, removing peak-hour throttling for Pro and Max accounts, and significantly raising the Claude Opus API rate limits — underwritten by a freshly signed deal to use the entire compute capacity of SpaceX's Colossus 1 data center in Memphis.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-08</news:publication_date>
      <news:title>Anthropic Doubles Claude Code Rate Limits — Here's What Changed and Why SpaceX Made It Possible</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/kimi-work</loc>
    <lastmod>2026-06-13T03:36:05.676Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/28c4bc20-430f-4495-a849-3503384b08b9</image:loc>
      <image:title>Kimi Work — 2026-06-12</image:title>
      <image:caption>You can now drag a bug-reproduction video into a coding agent and have it reason over the footage and the code together. That, not the 300-agent local swarm, is the feature in Moonshot's Kimi Work with no equivalent anywhere else, and the ACP protocol bet underneath it may matter more than either.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-12</news:publication_date>
      <news:title>Kimi Work — 2026-06-12</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-fable-5-is-out-anthropics-first-public-mythos-class-model-beats-gpt-55-by-21-points-on-swe-bench-pro</loc>
    <lastmod>2026-06-13T03:36:18.212Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/563f3db7-4271-4a9c-abcb-501f29bbb2f0</image:loc>
      <image:title>Claude Fable 5 Is Out: Anthropic's First Public Mythos-Class Model Beats GPT-5.5 by 21 Points on SWE-bench Pro</image:title>
      <image:caption>It scores ~80% on SWE-bench Pro, 21 points clear of GPT-5.5, and beat Pokemon FireRed from raw screenshots alone. But Fable 5 costs double Opus 4.8 the moment the free window closes June 22, and 'Mythos public' doesn't mean what the headlines imply.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-10</news:publication_date>
      <news:title>Claude Fable 5 Is Out: Anthropic's First Public Mythos-Class Model Beats GPT-5.5 by 21 Points on SWE-bench Pro</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-opus-48-same-price-a-3-cheaper-fast-mode-and-hundreds-of-parallel-subagents</loc>
    <lastmod>2026-06-13T03:34:35.518Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/3b3239ea-2391-4e3c-a27e-17f4d3208b7a</image:loc>
      <image:title>Claude Opus 4.8: Same Price, a 3× Cheaper Fast Mode, and Hundreds of Parallel Subagents</image:title>
      <image:caption>New flagship models almost always cost more. Opus 4.8 holds Opus 4.7's exact $5/$25 price, adds a fast mode that is 3x cheaper than older speed tiers, and is roughly 4x less likely to let its own buggy code pass unremarked.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Claude Opus 4.8: Same Price, a 3× Cheaper Fast Mode, and Hundreds of Parallel Subagents</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/microsofts-mai-code-1-flash-is-its-first-proprietary-coding-model</loc>
    <lastmod>2026-06-13T03:34:55.217Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/866e860a-c328-4450-895f-7028d10e412c</image:loc>
      <image:title>Microsoft's MAI-Code-1-Flash Is Its First Proprietary Coding Model</image:title>
      <image:caption>At $0.75/$4.50 per million tokens, Microsoft's first OpenAI-free coding model undercuts Claude Opus 4.8 roughly 6x and ships as a Copilot default in VS Code. The strategic threat to OpenAI isn't the benchmarks. It's the rerouting.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Microsoft's MAI-Code-1-Flash Is Its First Proprietary Coding Model</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/microsoft-build-2026-7-in-house-ai-models-the-scout-autopilot-agent-majorana-2-what-developers-need-to-know</loc>
    <lastmod>2026-06-13T03:35:34.238Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e85fc6cd-64f0-49a8-8c18-e004c4f6d6fb</image:loc>
      <image:title>Microsoft Build 2026: 7 In-House AI Models, the Scout Autopilot Agent & Majorana 2 — What Developers Need to Know</image:title>
      <image:caption>Microsoft spent three years renting frontier AI from OpenAI. At Build 2026 it became a competitor: seven in-house models, an always-on Scout agent built on OpenClaw, and a quantum chip whose 1,000x claim is still an unreviewed preprint. The four dates that affect what you can ship.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Microsoft Build 2026: 7 In-House AI Models, the Scout Autopilot Agent & Majorana 2 — What Developers Need to Know</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/hermes-agent-now-runs-free-on-owl-alpha-heres-the-catch</loc>
    <lastmod>2026-06-13T03:28:55.614Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/67ff0347-1479-4b85-a95e-da534aa3f706</image:loc>
      <image:title>Hermes Agent Now Runs Free on Owl Alpha — Here's the Catch</image:title>
      <image:caption>Point the open-source Hermes Agent at Owl Alpha — a free, 1M-token stealth model on OpenRouter — and you get an always-on AI agent with no API bill. The catch: about 12 tokens per second, a 4.7% tool-call error rate, and every prompt logged to train someone's next model.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Hermes Agent Now Runs Free on Owl Alpha — Here's the Catch</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/building-effective-ai-agents</loc>
    <lastmod>2026-06-13T03:36:33.681Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/dd2775dd-8139-46a1-a953-883aeba70fd5</image:loc>
      <image:title>Building Effective AI Agents</image:title>
      <image:caption>Anthropic studied dozens of teams shipping agents to production and found the best ones had something in common: they refused to build the elaborate orchestration frameworks everyone else was reaching for. Direct API calls won on debugging and cost. Here are the five patterns that actually survived.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Building Effective AI Agents</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/12-ai-coding-agents-compared-in-2026</loc>
    <lastmod>2026-06-11T15:50:27.211Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/901e7cbc-dcc9-40da-9721-79d32c7d1254</image:loc>
      <image:title>12 AI Coding Agents Compared in 2026 — 2026-06-08</image:title>
      <image:caption>A June 2026 benchmark roundup covering 12 AI coding agents finds Claude Opus 4.8 at the top of software engineering tasks — scoring 88.6% on SWE-bench Verified — while GPT-5.5 leads on terminal automation with 82.7% on Terminal-Bench 2.0.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>12 AI Coding Agents Compared in 2026 — 2026-06-08</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-io-2026-kicks-off-with-ai-model-coding-and-agent-updates</loc>
    <lastmod>2026-06-13T03:37:40.943Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/56dee0f3-b830-4311-a822-13c3f0546fc6</image:loc>
      <image:title>Google I/O 2026 Kicks Off With AI Model, Coding, and Agent Updates — 2026-06-08</image:title>
      <image:caption>Gemini 3.5 Flash posts 76.2% on Terminal-Bench 2.1 at Flash price, and that one number is reason enough to re-benchmark your default coding-agent model. Plus Antigravity 2.0's CLI, Managed Agents, and the WebMCP web standard, sorted for builders.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Google I/O 2026 Kicks Off With AI Model, Coding, and Agent Updates — 2026-06-08</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/microsofts-new-ai-models</loc>
    <lastmod>2026-06-13T03:37:43.122Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/bc0e6dec-2750-4b02-a57f-2676738f7d59</image:loc>
      <image:title>Microsoft's New AI Models — 2026-06-08</image:title>
      <image:caption>Microsoft's real Build 2026 story isn't two new models. It's a strategic bet to stop paying OpenAI per token. MAI-Code-1-Flash is live in Copilot today, but the headline 10x-cheaper-than-GPT-5-5 McKinsey number has exactly one unverifiable data point behind it.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Microsoft's New AI Models — 2026-06-08</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/introducing-claude-opus-48</loc>
    <lastmod>2026-06-13T03:37:38.768Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/1e4d2d1c-f52d-4bec-97ec-8901b579b832</image:loc>
      <image:title>Introducing Claude Opus 4.8</image:title>
      <image:caption>Upgrade from Claude 4.7 to Opus 4.8 and your bill goes down, not up: same base price, fast mode cut 3x. The features that actually change what you build are the three platform changes shipping alongside, not the benchmark bumps. Here's the upgrade decision tree.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-09</news:publication_date>
      <news:title>Introducing Claude Opus 4.8</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-mythos-5-surfaces-in-anthropics-api-catalog-as-leaked-slug-pricing-and-benchmark-outputs-point-to-imminent-release</loc>
    <lastmod>2026-06-13T03:37:36.557Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/2d0e4655-4e3f-4125-8714-03a7a700ad51</image:loc>
      <image:title>Claude Mythos 5 Surfaces in Anthropic's API Catalog as Leaked Slug, Pricing, and Benchmark Outputs Point to Imminent Release</image:title>
      <image:caption>A claude-mythos-5 slug appeared in Anthropic's API catalog and vanished. The evidence around it ranges from a 47% Polymarket bet to a real Zcash vulnerability that dropped the token 48%. Sorted by how much you should actually trust each piece.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-08</news:publication_date>
      <news:title>Claude Mythos 5 Surfaces in Anthropic's API Catalog as Leaked Slug, Pricing, and Benchmark Outputs Point to Imminent Release</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-mythos-5-leaked-gpt-56-checkpoints-purple-stealth-video-model</loc>
    <lastmod>2026-06-13T03:37:39.843Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/848b3e8a-c62b-4e00-95c8-2b4e0cdbb97a</image:loc>
      <image:title>Claude Mythos 5 Leaked + GPT 5.6 Checkpoints + Purple Stealth Video Model — 2026-06-08</image:title>
      <image:caption>Two leaks put Anthropic's next frontier model at two different prices: $16/$80 versus $25/$125 per million tokens. They can't both be right, and which one is tells you how to read the Mythos 5 demos, the GPT 5.6 checkpoint shuffle, and the stealth Purple video model.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-08</news:publication_date>
      <news:title>Claude Mythos 5 Leaked + GPT 5.6 Checkpoints + Purple Stealth Video Model — 2026-06-08</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/this-local-ai-agent-set-up-a-remote-machine-and-posted-to-telegram-completely-on-its-own</loc>
    <lastmod>2026-06-13T03:37:41.980Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/636cb28f-933c-46cf-b14d-7a2b24ad075a</image:loc>
      <image:title>This Local AI Agent Set Up a Remote Machine and Posted to Telegram Completely on Its Own</image:title>
      <image:caption>A 3B-active local model SSH'd into a second machine, installed image software it didn't have, generated a picture, and posted it to Telegram in 10-15 minutes with zero human input. The weights weren't the story. The harness was.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-05</news:publication_date>
      <news:title>This Local AI Agent Set Up a Remote Machine and Posted to Telegram Completely on Its Own</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropics-project-deal-let-69-employees-ai-agents-run-a-real-marketplace-and-the-smarter-model-won-every-time</loc>
    <lastmod>2026-06-13T03:37:37.657Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ca922cde-215e-4246-9db3-74d6b423d103</image:loc>
      <image:title>Anthropic's "Project Deal" Let 69 Employees' AI Agents Run a Real Marketplace — and the Smarter Model Won Every Time</image:title>
      <image:caption>When Anthropic secretly gave some agents a weaker model in a real 69-person marketplace, those agents got measurably worse prices, an Opus seller turned a $38 bike into $65, and the humans on the losing end rated their deals just as fair. The lesson for model selection isn't the obvious one.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-05</news:publication_date>
      <news:title>Anthropic's "Project Deal" Let 69 Employees' AI Agents Run a Real Marketplace — and the Smarter Model Won Every Time</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/nvidia-backs-openclaw-with-nemoclaw-what-the-250k-star-agent-platform-means-for-developers</loc>
    <lastmod>2026-06-13T03:35:55.971Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/cfceda67-6c93-4092-8485-df241baf78c2</image:loc>
      <image:title>NVIDIA Backs OpenClaw With NemoClaw — What the 250K-Star Agent Platform Means for Developers</image:title>
      <image:caption>250,000 GitHub stars in 60 days got a chipmaker to ship a hardened agent stack. Here's what 'persistent claws,' OpenShell sandboxing, and DGX Spark actually mean for how you'd build.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-05</news:publication_date>
      <news:title>NVIDIA Backs OpenClaw With NemoClaw — What the 250K-Star Agent Platform Means for Developers</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-sunsets-gemini-cli-for-antigravity-cli-what-changes-on-june-18</loc>
    <lastmod>2026-06-13T03:36:05.534Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/27d0c0a5-e29d-40f1-9238-c532de906a4d</image:loc>
      <image:title>Google Sunsets Gemini CLI for Antigravity CLI: What Changes on June 18</image:title>
      <image:caption>June 18 kills the Gemini CLI for individual Pro and Ultra users only. Enterprise licenses and paid API keys keep working. The fix is a tier check, not a panic.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-05</news:publication_date>
      <news:title>Google Sunsets Gemini CLI for Antigravity CLI: What Changes on June 18</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/windsurf-20s-kanban-agent-command-center-beats-vs-code-and-cursor-at-orchestration</loc>
    <lastmod>2026-06-13T03:35:58.438Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/aed2d74e-4700-4f5d-bfa0-cadad2a35941</image:loc>
      <image:title>Windsurf 2.0's Kanban Agent Command Center Beats VS Code and Cursor at Orchestration</image:title>
      <image:caption>Windsurf 2.0 borrows the one idea every other AI editor forgot to ship: a project board.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-05</news:publication_date>
      <news:title>Windsurf 2.0's Kanban Agent Command Center Beats VS Code and Cursor at Orchestration</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-drops-gemma-4-12b-encoder-free-multimodal-that-runs-on-your-laptop</loc>
    <lastmod>2026-06-13T03:36:00.750Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/530a5f2e-5bc0-4d79-8ab3-f1b77cd104da</image:loc>
      <image:title>Google Drops Gemma 4 12B: Encoder-Free Multimodal That Runs on Your Laptop</image:title>
      <image:caption>The most interesting thing about Gemma 4 12B isn't a benchmark. It's a deletion: Google threw out the encoders every rival multimodal model relies on, and it fits in 16GB.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-04</news:publication_date>
      <news:title>Google Drops Gemma 4 12B: Encoder-Free Multimodal That Runs on Your Laptop</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/minimax-m3-open-weight-frontier-model-beats-gpt-55-on-code-agentic-benchmarks</loc>
    <lastmod>2026-06-13T03:36:03.235Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/17edcd4e-e13d-4cba-a6a4-a1dcb06188e3</image:loc>
      <image:title>MiniMax M3 — Open-Weight Frontier Model Beats GPT-5.5 on Code & Agentic Benchmarks — 2026-06-01</image:title>
      <image:caption>MiniMax M3 took an Nvidia Hopper GPU from 7.6% to 71.3% utilization in a 24-hour autonomous run, no human touch. The weights are public. The catch is what the demo doesn't show.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-06-02</news:publication_date>
      <news:title>MiniMax M3 — Open-Weight Frontier Model Beats GPT-5.5 on Code & Agentic Benchmarks — 2026-06-01</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/github-slashes-agent-token-spend-62</loc>
    <lastmod>2026-05-30T16:06:21.976Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/1040805b-abad-4d7b-a2ed-f2e07361e680</image:loc>
      <image:title>GitHub Slashes Agent Token Spend 62% — 2026-05-30</image:title>
      <image:caption>GitHub published production data on May 30, 2026, showing it cut token costs in its own agentic CI workflows by as much as 62% — not through model swaps or architectural rewrites, but through disciplined measurement, schema pruning, and a p</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-30</news:publication_date>
      <news:title>GitHub Slashes Agent Token Spend 62% — 2026-05-30</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-design-claude-code-the-design-first-workflow-is-taking-off-in-2026</loc>
    <lastmod>2026-06-04T03:23:15.717Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/a1990fbb-f716-41e9-8c8b-014a7de584ef</image:loc>
      <image:title>Claude Design + Claude Code: The Design-First Workflow Is Taking Off in 2026</image:title>
      <image:caption>Claude Design + Claude Code: The Design-First Workflow Is Taking Off in 2026 A new way of building software with AI is consolidating in 2026, and it inverts the order most people have used for the past two years.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-30</news:publication_date>
      <news:title>Claude Design + Claude Code: The Design-First Workflow Is Taking Off in 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-prototype-tax-a-weekend-in-claude-design-saves-3-weeks-of-claude-code</loc>
    <lastmod>2026-05-30T13:03:49.458Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/8f079b0f-31b2-413f-ad7e-246278f81767</image:loc>
      <image:title>The Prototype Tax — A Weekend in Claude Design Saves 3 Weeks of Claude Code — 2026-05-30</image:title>
      <image:caption>Ashwin Francis and Raghav Mehra published a detailed workflow this week arguing that a single weekend spent prototyping in Claude Design can eliminate up to three weeks of wasted Claude Code iterations — a claim that cuts against how most s</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-30</news:publication_date>
      <news:title>The Prototype Tax — A Weekend in Claude Design Saves 3 Weeks of Claude Code — 2026-05-30</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/autoclaw-copaw-and-the-openclaw-wave-vendor-packaged-vs-self-hosted-im-native-agents</loc>
    <lastmod>2026-06-04T03:20:44.894Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/af4a6f6e-5334-4e06-a917-526dde455a2a</image:loc>
      <image:title>AutoClaw, CoPaw, and the OpenClaw Wave: Vendor-Packaged vs Self-Hosted IM-Native Agents</image:title>
      <image:caption>AutoClaw, CoPaw, and the OpenClaw Wave: Vendor-Packaged vs Self-Hosted IM-Native Agents If you have been reading about "AutoClaw vs OpenClaw" as if they were rival products fighting for the same users, it is worth pausing to clear up a...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-30</news:publication_date>
      <news:title>AutoClaw, CoPaw, and the OpenClaw Wave: Vendor-Packaged vs Self-Hosted IM-Native Agents</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/grok-build-01-is-now-in-your-ide-via-kilo-code</loc>
    <lastmod>2026-05-29T19:05:39.583Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/1ab7b8fa-e455-4d21-b367-187780086cb0</image:loc>
      <image:title>Grok Build 0.1 Is Now in Your IDE, via Kilo Code</image:title>
      <image:caption>Grok Build 0.1 Is Now in Your IDE, via Kilo Code xAI just put its coding model where developers actually work — inside the editor.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-29</news:publication_date>
      <news:title>Grok Build 0.1 Is Now in Your IDE, via Kilo Code</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/perplexitys-bumblebee-scans-your-mcp-configs-for-supply-chain-threats-without-running-a-thing</loc>
    <lastmod>2026-05-29T18:05:45.638Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ef87b704-1fae-49e3-b061-5a5b72cf8d29</image:loc>
      <image:title>Perplexity's Bumblebee Scans Your MCP Configs for Supply-Chain Threats — Without Running a Thing</image:title>
      <image:caption>Your MCP config files now sit in the same blast radius as your lockfiles.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-29</news:publication_date>
      <news:title>Perplexity's Bumblebee Scans Your MCP Configs for Supply-Chain Threats — Without Running a Thing</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/xai-brings-grok-to-kilo-code-ide</loc>
    <lastmod>2026-05-29T12:57:10.578Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/27e7398d-d354-49b2-adc8-1b4eff206d6e</image:loc>
      <image:title>xAI Brings Grok to Kilo Code IDE — 2026-05-29</image:title>
      <image:caption>xAI announced on May 29, 2026 that a new model called `grok-build-0.1` — purpose-built for agentic coding — is now available inside Kilo Code, a VS Code-based AI coding IDE.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-29</news:publication_date>
      <news:title>xAI Brings Grok to Kilo Code IDE — 2026-05-29</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/microsoft-365-copilot-redesign</loc>
    <lastmod>2026-05-29T12:56:31.078Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c8c5cbaa-5f92-4a40-944e-6135df656d8f</image:loc>
      <image:title>Microsoft 365 Copilot Redesign — 2026-05-29</image:title>
      <image:caption>Microsoft's redesign of its 365 Copilot app, announced May 28 by Chief Design Officer Jon Friedman, produced usage increases of 27 to 43 percent across Word, Excel, PowerPoint, and Outlook — numbers that land hard enough to deserve more tha</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-29</news:publication_date>
      <news:title>Microsoft 365 Copilot Redesign — 2026-05-29</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/autoclaw-vs-openclaw-two-approaches-to-im-native-ai-agents</loc>
    <lastmod>2026-06-04T04:31:53.897Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/7f2994ec-db12-4c67-b180-28f1e0943879</image:loc>
      <image:title>AutoClaw vs OpenClaw: Two Approaches to IM-Native AI Agents</image:title>
      <image:caption>AutoClaw vs OpenClaw: Two Approaches to IM-Native AI Agents A new desktop app called AutoClaw, built by the team behind AutoGLM at Chinese AI lab Zhipu (z.ai), is the latest entrant in a category that is quietly becoming one of the most...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-29</news:publication_date>
      <news:title>AutoClaw vs OpenClaw: Two Approaches to IM-Native AI Agents</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/hermes-agent-deepseek-v4-flash-now-free-zero-cost-autonomous-agent-stack</loc>
    <lastmod>2026-06-04T04:31:10.594Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/f0efc2db-c0c2-4433-8c8f-ea06677c19e5</image:loc>
      <image:title>Hermes Agent + DeepSeek V4 Flash Now Free — Zero-Cost Autonomous Agent Stack — 2026-05-28</image:title>
      <image:caption>Nous Research quietly made one of the more interesting moves in the open-source agent space this week: DeepSeek V4 Flash is now available for free inside Hermes Agent, the company's MIT-licensed persistent agent harness — giving developers</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-28</news:publication_date>
      <news:title>Hermes Agent + DeepSeek V4 Flash Now Free — Zero-Cost Autonomous Agent Stack — 2026-05-28</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/openclaw-524-beta-discord-voice-meeting-notes-imessage-approvals-real-time-agent-steering</loc>
    <lastmod>2026-06-04T03:17:22.716Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/97ce939a-7b4f-4e61-bfb3-f463fdf8a0f2</image:loc>
      <image:title>OpenClaw 5.24 Beta — Discord Voice Meeting Notes, iMessage Approvals & Real-Time Agent Steering — 2026-05-28</image:title>
      <image:caption>OpenClaw 5.24 beta, released to GitHub on May 28, 2026, ships three features that together signal a meaningful shift in how AI agents handle real-world coordination: automatic Discord voice transcription for meeting notes, emoji-based appro</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-28</news:publication_date>
      <news:title>OpenClaw 5.24 Beta — Discord Voice Meeting Notes, iMessage Approvals & Real-Time Agent Steering — 2026-05-28</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/hermes-agent-os-promises-fully-autonomous-seo-heres-what-developers-should-know</loc>
    <lastmod>2026-05-29T02:22:27.060Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/aacb3a37-0bc3-491a-8dd5-a76338249f48</image:loc>
      <image:title>Hermes Agent OS Promises Fully Autonomous SEO — Here's What Developers Should Know</image:title>
      <image:caption>Hermes Agent OS Promises Fully Autonomous SEO — Here's What Developers Should Know A new open-architecture AI system called Hermes is making waves in the AI-tooling community, with its creator Julian Goldie claiming it can autonomously...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-26</news:publication_date>
      <news:title>Hermes Agent OS Promises Fully Autonomous SEO — Here's What Developers Should Know</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/workos-auth-agent-registration-protocol</loc>
    <lastmod>2026-06-04T04:30:25.881Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/29fd05f3-e934-43a9-8dd8-064a36d7ed56</image:loc>
      <image:title>WorkOS auth — Agent Registration Protocol</image:title>
      <image:caption>WorkOS published **auth.md** on May 25, 2026 — an open protocol that lets AI agents autonomously discover, register with, and obtain scoped credentials from any web service without a human pasting in an API key.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-26</news:publication_date>
      <news:title>WorkOS auth — Agent Registration Protocol</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-antigravity-20-turns-multi-day-engineering-sprints-into-hours-with-93-agent-parallelism</loc>
    <lastmod>2026-05-29T02:02:07.979Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/df9a9c85-d124-4851-8b31-7d56e1a50c6c</image:loc>
      <image:title>Google Antigravity 2.0 Turns Multi-Day Engineering Sprints Into Hours With 93-Agent Parallelism</image:title>
      <image:caption>Google Antigravity 2.0 Turns Multi-Day Engineering Sprints Into Hours With 93-Agent Parallelism Google unveiled Antigravity 2.0 at its I/O 2026 keynote on May 22, 2026 — a ground-up redesign of its AI-powered developer IDE that bets...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-24</news:publication_date>
      <news:title>Google Antigravity 2.0 Turns Multi-Day Engineering Sprints Into Hours With 93-Agent Parallelism</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-sunsets-gemini-cli-replaces-it-with-antigravity-cli-as-multi-agent-era-begins</loc>
    <lastmod>2026-06-04T02:22:02.338Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/32ec96a6-6e23-4082-b787-b9f0b8064904</image:loc>
      <image:title>Google Sunsets Gemini CLI, Replaces It With Antigravity CLI as Multi-Agent Era Begins</image:title>
      <image:caption>Google Sunsets Gemini CLI, Replaces It With Antigravity CLI as Multi-Agent Era Begins Google has announced it is discontinuing Gemini CLI — one of the most rapidly adopted developer tools in recent memory — and replacing it with...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-23</news:publication_date>
      <news:title>Google Sunsets Gemini CLI, Replaces It With Antigravity CLI as Multi-Agent Era Begins</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/build-your-ai-testing-pipeline</loc>
    <lastmod>2026-05-29T01:57:45.539Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/6df9853d-d5f5-4fc9-a015-322841967f23</image:loc>
      <image:title>Build Your AI Testing Pipeline — 2026-05-23</image:title>
      <image:caption>---</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-23</news:publication_date>
      <news:title>Build Your AI Testing Pipeline — 2026-05-23</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-io-2026-recap-everything-announced</loc>
    <lastmod>2026-05-29T01:57:02.953Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/4e412916-4301-4045-bfc9-13f54b220dde</image:loc>
      <image:title>Google I/O 2026 Recap: Everything Announced</image:title>
      <image:caption>Google held its annual I/O developer conference in May 2026, and the through-line across every keynote segment was the same: Gemini is no longer a chatbot. It is an agent layer wired into nearly everything Google ships.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-23</news:publication_date>
      <news:title>Google I/O 2026 Recap: Everything Announced</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/microsoft-copilot-chat-everything-new-in-outlook-teams-m365</loc>
    <lastmod>2026-05-29T01:56:20.570Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/27d8ca5f-ce00-4338-b7b6-6c8cfb789837</image:loc>
      <image:title>Microsoft Copilot Chat — Everything New in Outlook, Teams & M365 — 2026-05-23</image:title>
      <image:caption>Microsoft's Copilot Chat, embedded directly inside Outlook and Teams for an estimated 400 to 500 million Office users, now includes a model selector that puts Anthropic's Claude Opus and OpenAI's GPT-5.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-23</news:publication_date>
      <news:title>Microsoft Copilot Chat — Everything New in Outlook, Teams & M365 — 2026-05-23</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/my-top-3-takeaways-from-code-with-claude-2026-claudepartner-claude-ai-claude</loc>
    <lastmod>2026-05-29T01:55:37.975Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/7f7262db-e008-4405-b3a0-3379921bb7d2</image:loc>
      <image:title>My Top 3 Takeaways From Code With Claude 2026</image:title>
      <image:caption>At Anthropic's Code with Claude 2026 event, three features stood out to creators covering the conference: a self-grading technique called Outcomes, a direct handoff path from Claude Design to Claude Code, and a scheduled memory-consolidatio</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-23</news:publication_date>
      <news:title>My Top 3 Takeaways From Code With Claude 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/spacexai-prepares-grok-build-desktop-app-to-rival-openai-codex</loc>
    <lastmod>2026-05-29T01:54:56.075Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c4c9e779-50cb-4729-a11c-1b3ceee7f7ef</image:loc>
      <image:title>SpaceXAI Prepares Grok Build Desktop App to Rival OpenAI Codex — 2026-05-23</image:title>
      <image:caption>xAI, the AI company rebranded under the SpaceXAI umbrella, is preparing to launch Grok Build — a cross-platform desktop coding application targeting macOS, Linux, and Windows simultaneously — in a direct move against both Claude Code and Op</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-23</news:publication_date>
      <news:title>SpaceXAI Prepares Grok Build Desktop App to Rival OpenAI Codex — 2026-05-23</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/base44s-real-move-isnt-the-agent-its-the-bundle</loc>
    <lastmod>2026-05-18T22:57:27.229Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e7bec18c-fb47-45c1-9164-30f8c0cda7aa</image:loc>
      <image:title>Base44's Real Move Isn't the Agent — It's the Bundle</image:title>
      <image:caption>Base44's Real Move Isn't the Agent — It's the Bundle Base44, the Wix-owned vibe-coding platform, has folded a full autonomous-agent layer — Superagents — into the same product that already lets non-developers build apps from a prompt.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-18</news:publication_date>
      <news:title>Base44's Real Move Isn't the Agent — It's the Bundle</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/openhuman-the-open-source-ai-agent-that-wants-to-replace-openclaw-and-hermes</loc>
    <lastmod>2026-06-04T04:26:36.379Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b43e6151-e230-4151-a0d5-239fb064ce58</image:loc>
      <image:title>OpenHuman: The Open-Source AI Agent That Wants to Replace OpenClaw and Hermes</image:title>
      <image:caption>OpenHuman: The Open-Source AI Agent That Wants to Replace OpenClaw and Hermes A new open-source desktop agent called OpenHuman went from a few hundred GitHub stars to roughly 14,000 in under a week, and the pitch behind that spike is...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-18</news:publication_date>
      <news:title>OpenHuman: The Open-Source AI Agent That Wants to Replace OpenClaw and Hermes</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/xai-launches-grok-build-an-agentic-coding-cli-in-early-beta</loc>
    <lastmod>2026-06-04T04:24:57.845Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ad54a365-c290-4b7d-9263-543ca7fa1a9a</image:loc>
      <image:title>xAI Launches Grok Build, an Agentic Coding CLI, in Early Beta</image:title>
      <image:caption>xAI Launches Grok Build, an Agentic Coding CLI, in Early Beta xAI has entered the agentic coding tools market with Grok Build, a command-line coding agent for professional software engineering that the company introduced in early beta on...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-17</news:publication_date>
      <news:title>xAI Launches Grok Build, an Agentic Coding CLI, in Early Beta</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/one-folder-runs-claude-codex-gemini-and-obsidian-the-anti-lock-in-memory-pattern-going-around</loc>
    <lastmod>2026-05-18T22:54:07.572Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/22c94245-1720-4efb-b162-af07e3cb7ca3</image:loc>
      <image:title>One Folder Runs Claude, Codex, Gemini — and Obsidian. The Anti-Lock-In Memory Pattern Going Around</image:title>
      <image:caption>One Folder Runs Claude, Codex, Gemini — and Obsidian.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-17</news:publication_date>
      <news:title>One Folder Runs Claude, Codex, Gemini — and Obsidian. The Anti-Lock-In Memory Pattern Going Around</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/unity-6-launches-official-mcp-server-claude-code-and-cursor-can-now-see-inside-your-game-scene</loc>
    <lastmod>2026-06-04T04:28:44.847Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/3886420a-378f-431a-89f8-755b34978c90</image:loc>
      <image:title>Unity 6 Launches Official MCP Server — Claude Code and Cursor Can Now See Inside Your Game Scene</image:title>
      <image:caption>Unity 6 Launches Official MCP Server — Claude Code and Cursor Can Now See Inside Your Game Scene Unity has shipped a built-in Model Context Protocol (MCP) server as part of Unity AI, which entered open beta in May 2026 for everyone running...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-15</news:publication_date>
      <news:title>Unity 6 Launches Official MCP Server — Claude Code and Cursor Can Now See Inside Your Game Scene</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/hidream-o1-image-debuts-at-8-on-artificial-analysis-arena-and-you-can-run-it-locally-in-comfyui-today</loc>
    <lastmod>2026-06-04T04:24:01.798Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/d8ff9ab1-2cbc-44cb-8c85-662643a08f6d</image:loc>
      <image:title>HiDream-O1-Image Debuts at #8 on Artificial Analysis Arena — and You Can Run It Locally in ComfyUI Today</image:title>
      <image:caption>HiDream-O1-Image Debuts at 8 on Artificial Analysis Arena — and You Can Run It Locally in ComfyUI Today On May 8, 2026, [HiDream-ai open-sourced HiDream-O1-Image](https://github.com/HiDream-ai/HiDream-O1-Image) under the MIT license — an...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-15</news:publication_date>
      <news:title>HiDream-O1-Image Debuts at #8 on Artificial Analysis Arena — and You Can Run It Locally in ComfyUI Today</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/every-frontier-ai-model-scored-0-on-programbench-metas-benchmark-that-asks-models-to-rebuild-real-software-from-a-binary</loc>
    <lastmod>2026-05-18T22:52:28.730Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/68355e9d-542a-4f0e-b1fb-a7076a717ca3</image:loc>
      <image:title>Every Frontier AI Model Scored 0% on ProgramBench — Meta's Benchmark That Asks Models to Rebuild Real Software From a Binary</image:title>
      <image:caption>Every Frontier AI Model Scored 0% on ProgramBench — Meta's Benchmark That Asks Models to Rebuild Real Software From a Binary A new benchmark from Meta, Stanford, and Harvard just handed every top AI model a score of 0% — and if you develop...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-15</news:publication_date>
      <news:title>Every Frontier AI Model Scored 0% on ProgramBench — Meta's Benchmark That Asks Models to Rebuild Real Software From a Binary</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-weekly-recgen-hidream-o1-zia-8b-alphaevolve-more-2026-05-14</loc>
    <lastmod>2026-06-04T04:22:43.767Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ccfad06c-d386-488a-a59f-f162947240d4</image:loc>
      <image:title>AI Weekly — RecGen, HiDream O1, Zia 8B, AlphaEvolve & More — 2026-05-14</image:title>
      <image:caption># AI Weekly: Every Top Model Scored 0% on ProgramBench, Gemma 4 Hits 3× Speedup, and Open-Source Image Generation Has a New Leader</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-15</news:publication_date>
      <news:title>AI Weekly — RecGen, HiDream O1, Zia 8B, AlphaEvolve & More — 2026-05-14</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/grok-43-three-times-faster-five-times-more-context-half-the-price-2026-05-14</loc>
    <lastmod>2026-06-04T13:08:29.570Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/d7f4ea88-706e-410b-8648-98e74c7a649d</image:loc>
      <image:title>Grok 4.3: Three Times Faster, Five Times More Context, Half the Price — 2026-05-14</image:title>
      <image:caption>xAI shipped Grok 4.3 this week with a specification sheet that should make API budget managers sit up: a 1–2 million token context window, independent benchmark speeds of 235 tokens per second, and input pricing of $1.25 per million tokens.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-15</news:publication_date>
      <news:title>Grok 4.3: Three Times Faster, Five Times More Context, Half the Price — 2026-05-14</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropic-doubles-rate-limits-unveils-infinite-context-and-bets-on-multi-agent-orchestration-at-code-with-claude-conference</loc>
    <lastmod>2026-06-04T04:22:10.256Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/cde6b490-8ec6-4480-aa85-c5ff99aaa508</image:loc>
      <image:title>Anthropic Doubles Rate Limits, Unveils Infinite Context, and Bets on Multi-Agent Orchestration at Code with Claude Conference</image:title>
      <image:caption>Anthropic Doubles Rate Limits, Unveils Infinite Context, and Bets on Multi-Agent Orchestration at Code with Claude Conference Anthropic used its "Code with Claude" developer conference in early May 2026 to announce the most significant...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-15</news:publication_date>
      <news:title>Anthropic Doubles Rate Limits, Unveils Infinite Context, and Bets on Multi-Agent Orchestration at Code with Claude Conference</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/grafana-assistant-claude-code-ai-powered-telemetry-debugging-2026-05-14</loc>
    <lastmod>2026-06-04T04:23:20.837Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/95b133d5-85cf-4edc-8adb-acddd76b4057</image:loc>
      <image:title>Grafana Assistant + Claude Code: AI-Powered Telemetry Debugging — 2026-05-14</image:title>
      <image:caption>Grafana's AI assistant and Claude Code combined to close a frontend bug on May 14, 2026 — without a developer ever opening a log viewer.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-14</news:publication_date>
      <news:title>Grafana Assistant + Claude Code: AI-Powered Telemetry Debugging — 2026-05-14</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-product-launches-news-may-2026-startup-edition</loc>
    <lastmod>2026-06-04T04:20:52.877Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/6f2241ec-2877-4bd4-9b44-c2f10f2394f0</image:loc>
      <image:title>AI Product Launches News | May 2026 (Startup Edition)</image:title>
      <image:caption>DeepSeek's V4 Flash and Pro models arrived in May 2026 with 1-million-token context windows priced well below what frontier labs currently charge — and that single fact is enough to force a rethink of how development teams allocate their AI</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI Product Launches News | May 2026 (Startup Edition)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-biggest-ai-stories-of-the-year-so-far</loc>
    <lastmod>2026-06-04T04:20:13.307Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/bdb93ff1-579e-4737-b33c-7bacbdecb727</image:loc>
      <image:title>The Biggest AI Stories of the Year (So Far)</image:title>
      <image:caption>By March 13, 2026, three stories had already reshaped the AI industry more than most years manage in twelve months: a governance standoff between Anthropic and the Pentagon, two high-profile acqui-hires that validated the agentic AI playboo</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>The Biggest AI Stories of the Year (So Far)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/image-ai-models-now-drive-app-growth-2026-05-11</loc>
    <lastmod>2026-06-04T04:19:57.172Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/3c945840-9bb4-4e52-b724-a795788d3481</image:loc>
      <image:title>Image AI Models Now Drive App Growth — 2026-05-11</image:title>
      <image:caption>Image AI releases are now the single most powerful growth lever in consumer AI apps, generating 6.5 times more downloads than traditional chatbot or LLM upgrades, according to Appfigures data cited by TechCrunch on May 4, 2026.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>Image AI Models Now Drive App Growth — 2026-05-11</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-may-2026-aitoolsrecap-2026-05-11</loc>
    <lastmod>2026-06-04T13:08:12.632Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/bffdd5ac-1446-4c74-80e4-7e836b67d060</image:loc>
      <image:title>AI News May 2026 — AIToolsRecap | 2026-05-11</image:title>
      <image:caption>Anthropic crossed $44 billion in annualized revenue in Q1 2026 — an 80x increase year-over-year — and paired that milestone with a compute deal that immediately doubled Claude Code rate limits for developers.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI News May 2026 — AIToolsRecap | 2026-05-11</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-category-digest-may-11-2026</loc>
    <lastmod>2026-05-25T21:43:01.712Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/962186c5-f66e-4603-ba35-5b0f6d17d32c</image:loc>
      <image:title>AI Category Digest — May 11, 2026</image:title>
      <image:caption>On May 11, 2026, three distinct forces are pulling AI infrastructure in the same direction: platforms are racing to own audio and voice as a distribution layer, chip makers are rewriting their business models as equity investors, and safety</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI Category Digest — May 11, 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-category-roundup-may-11-2026</loc>
    <lastmod>2026-05-25T21:43:09.667Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/87d05dde-6b28-4bdb-9fb2-b38df58f26dd</image:loc>
      <image:title>AI Category Roundup — May 11, 2026</image:title>
      <image:caption>Cloudflare confirmed this week that artificial intelligence automation made 1,100 roles obsolete — while the company simultaneously posted record revenue — giving the tech industry one of its most concrete data points yet on what AI-driven</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI Category Roundup — May 11, 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-in-may-2026-the-model-wave-agentic-shift-and-power-crisis</loc>
    <lastmod>2026-06-04T04:19:18.649Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/5978a7f3-4ba2-4963-a74c-799f7b2573c0</image:loc>
      <image:title>AI in May 2026: The Model Wave, Agentic Shift and Power Crisis</image:title>
      <image:caption>May 2026 is delivering the densest model release cycle since the GPT-4 era, with GPT-5.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI in May 2026: The Model Wave, Agentic Shift and Power Crisis</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-roundup-may-11-2026</loc>
    <lastmod>2026-05-25T21:43:09.716Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/1149cf05-9386-4789-954a-fb3141ed957d</image:loc>
      <image:title>AI Roundup — May 11, 2026</image:title>
      <image:caption>OpenAI quietly added voice intelligence capabilities to its developer API this week, handing builders real-time audio input and output for the first time — a move that puts the company in direct competition with ElevenLabs and AssemblyAI on</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI Roundup — May 11, 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropic-hits-44b-arr-with-80x-growth-doubles-claude-code-limits-may-2026-ai-roundup</loc>
    <lastmod>2026-06-05T16:45:44.429Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/7fec0763-795d-498c-b1e5-707bec8b4d2f</image:loc>
      <image:title>Anthropic Hits $44B ARR With 80x Growth, Doubles Claude Code Limits — May 2026 AI Roundup</image:title>
      <image:caption>Anthropic crossed $44 billion in annualized revenue in May 2026 — an 80x increase year-over-year — and immediately put that growth to work by securing access to SpaceX's Colossus 1 supercomputer, a 300-megawatt facility housing more than 22</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>Anthropic Hits $44B ARR With 80x Growth, Doubles Claude Code Limits — May 2026 AI Roundup</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropic-arr-crosses-44b-after-80-growth-agent-sdk-now-open-to-all-developers</loc>
    <lastmod>2026-06-04T04:18:15.940Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/dda6c800-c347-4538-9350-257616b0f8bf</image:loc>
      <image:title>Anthropic ARR Crosses $44B After 80× Growth — Agent SDK Now Open to All Developers</image:title>
      <image:caption>Anthropic disclosed this week that its annualized revenue has surpassed $44 billion — an 80× increase year-over-year — making it one of the fastest-growing enterprise software companies in recorded history.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>Anthropic ARR Crosses $44B After 80× Growth — Agent SDK Now Open to All Developers</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-headlines-roundup-may-11-2026</loc>
    <lastmod>2026-05-25T21:43:09.664Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/09a9fe66-4705-43e1-b45e-2a0907d88696</image:loc>
      <image:title>AI Headlines Roundup — May 11, 2026</image:title>
      <image:caption>Anthropic's Mythos tool is now running inside Mozilla's Firefox security pipeline — not as a chatbot assistant, but as an active auditor reading live code paths and surfacing vulnerabilities at production scale.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI Headlines Roundup — May 11, 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-may-2026-every-major-release-deal-and-announcement-2026-05-11</loc>
    <lastmod>2026-06-04T04:18:00.430Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/079743de-5976-487d-9367-aa63efe34a49</image:loc>
      <image:title>AI News May 2026 — Every Major Release, Deal, and Announcement — 2026-05-11</image:title>
      <image:caption>Anthropic disclosed annual recurring revenue above $44 billion — an 80x year-over-year increase — while simultaneously signing a 220,000+ GPU contract with SpaceX's Colossus 1 facility, opening its Claude Agent SDK to all external developer</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI News May 2026 — Every Major Release, Deal, and Announcement — 2026-05-11</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/image-ai-models-now-drive-app-growth-beating-chatbot-upgrades-2026-05-11</loc>
    <lastmod>2026-06-04T04:17:14.643Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/aefc3430-e9ac-4a6d-9146-30fa9fec0b36</image:loc>
      <image:title>Image AI Models Now Drive App Growth, Beating Chatbot Upgrades — 2026-05-11</image:title>
      <image:caption>Image model releases now drive **6.5 times more app downloads** than traditional chatbot or text model upgrades, according to new data from app analytics firm Appfigures — and the gap is wide enough that it's reshaping how AI companies thin</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>Image AI Models Now Drive App Growth, Beating Chatbot Upgrades — 2026-05-11</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-artificial-intelligence-techcrunch</loc>
    <lastmod>2026-06-04T04:16:53.150Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/9d16c357-ba5a-41f3-a3bf-ae08c316ed86</image:loc>
      <image:title>AI News & Artificial Intelligence — May 2026</image:title>
      <image:caption>On May 11, 2026, OpenAI expanded its API to include real-time voice intelligence — audio in, audio out, with latency low enough to power live conversations — putting it in direct competition with specialized voice platforms that have owned</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>AI News & Artificial Intelligence — May 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/vibe-coding-2026-build-your-first-app-in-30-minutes-2026-05-11</loc>
    <lastmod>2026-06-05T16:44:47.555Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c32b45a1-73c0-4d7e-9b0f-9302aee47ec6</image:loc>
      <image:title>Vibe Coding 2026: Build Your First App in 30 Minutes — 2026-05-11</image:title>
      <image:caption>By May 2026, more than 78 percent of working developers report using AI assistance on at least some of their code — a figure from GitHub's Octoverse 2025 report that would have seemed implausible three years ago.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-11</news:publication_date>
      <news:title>Vibe Coding 2026: Build Your First App in 30 Minutes — 2026-05-11</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-may-2026-all-model-releases-announcements-and-launches</loc>
    <lastmod>2026-06-04T04:15:48.983Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/d7495731-15f9-4062-8c81-4cea1208697e</image:loc>
      <image:title>AI News May 2026 — All Model Releases, Announcements and Launches</image:title>
      <image:caption>GPT-5.5 hit 82.7% on Terminal-Bench this month, Gemini 3.1 Ultra arrived with a 2-million token context window, and Mistral dropped a 128-billion parameter open-weights model — all within the same few weeks.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-10</news:publication_date>
      <news:title>AI News May 2026 — All Model Releases, Announcements and Launches</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-may-2026-2026-05-10</loc>
    <lastmod>2026-05-18T22:37:11.369Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b4c8ab0d-11ac-454e-b9fa-0c4c9b97a741</image:loc>
      <image:title>AI News May 2026 — 2026-05-10</image:title>
      <image:caption>GPT-5.5 scored 82.7% on Terminal-Bench 2.0 and 58.6% on SWE-Bench Pro when OpenAI released it on April 23, making it the current leader in agentic coding benchmarks — but it didn't hold the spotlight alone for long.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-10</news:publication_date>
      <news:title>AI News May 2026 — 2026-05-10</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/wyndham-launches-native-chatgpt-app-2026-05-10</loc>
    <lastmod>2026-06-04T04:14:43.985Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/481671ad-53cb-4e68-a14e-e19773a69997</image:loc>
      <image:title>Wyndham Launches Native ChatGPT App — 2026-05-10</image:title>
      <image:caption>Wyndham Hotels & Resorts became the first major U.S.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-10</news:publication_date>
      <news:title>Wyndham Launches Native ChatGPT App — 2026-05-10</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-may-2026-every-model-release-launch-and-announcement-tracked-daily-2026-05-10</loc>
    <lastmod>2026-06-04T04:14:05.190Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/0fc7a047-6cde-4e5f-a912-7c4b68e92661</image:loc>
      <image:title>AI News May 2026 — Every Model Release, Launch and Announcement Tracked Daily — 2026-05-10</image:title>
      <image:caption>May 2026 opened with at least four significant AI releases in its first three days alone: Gemini 3.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-10</news:publication_date>
      <news:title>AI News May 2026 — Every Model Release, Launch and Announcement Tracked Daily — 2026-05-10</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-gemini-s-skills-long-running-agents-make-it-a-real-workflow-os</loc>
    <lastmod>2026-06-04T04:13:49.570Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/20391205-2812-455b-8977-93615d219359</image:loc>
      <image:title>Google Gemini's Skills + Long-Running Agents Make It a Real Workflow OS</image:title>
      <image:caption>Google Gemini's Skills + Long-Running Agents Make It a Real Workflow OS At Google Cloud Next '26 in April, Google rewired Workspace from a tool you operate into a platform that operates on your direction.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-10</news:publication_date>
      <news:title>Google Gemini's Skills + Long-Running Agents Make It a Real Workflow OS</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/gpt-5-5-is-live-better-coding-document-grounding-and-computer-use-across-chatgpt-codex</loc>
    <lastmod>2026-06-04T04:16:35.835Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c6132f32-f3b4-4ea0-9fd1-b332468bf7d2</image:loc>
      <image:title>GPT-5.5 Is Live: Better Coding, Document Grounding, and Computer Use Across ChatGPT + Codex</image:title>
      <image:caption>GPT-5.5 Is Live: Better Coding, Document Grounding, and Computer Use Across ChatGPT + Codex OpenAI shipped GPT-5.5 on April 23, 2026, then quietly made GPT-5.5 Instant the default ChatGPT model on May 5.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-10</news:publication_date>
      <news:title>GPT-5.5 Is Live: Better Coding, Document Grounding, and Computer Use Across ChatGPT + Codex</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropic-s-next-claude-model-leaks-through-an-npm-mistake-and-the-details-are-significant</loc>
    <lastmod>2026-06-04T04:13:05.011Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/8da62930-d00c-4d26-87e5-bd0a11eaac1d</image:loc>
      <image:title>Anthropic's Next Claude Model Leaks Through an npm Mistake — and the Details Are Significant</image:title>
      <image:caption>Anthropic's Next Claude Model Leaks Through an npm Mistake — and the Details Are Significant An accidental developer error at Anthropic last month has handed the AI community its clearest look yet at the company's near-term roadmap,...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Anthropic's Next Claude Model Leaks Through an npm Mistake — and the Details Are Significant</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/karpathy-s-self-evolving-llm-wiki-5-minute-setup-with-claude-code-obsidian-2026-05-09</loc>
    <lastmod>2026-06-04T04:12:27.602Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/17992226-ddf3-451b-bc4d-6a05bbd3dce5</image:loc>
      <image:title>Karpathy's Self-Evolving LLM Wiki — 5-Minute Setup with Claude Code & Obsidian — 2026-05-09</image:title>
      <image:caption>Andrej Karpathy published a public gist in early 2026 outlining a self-evolving personal knowledge system — and a recent tutorial video demonstrates how to get a working version running in under five minutes using Claude Code and Obsidian.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Karpathy's Self-Evolving LLM Wiki — 5-Minute Setup with Claude Code & Obsidian — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/higgsfield-ai-s-cinema-studio-2-5-brings-end-to-end-production-control-to-ai-filmmaking</loc>
    <lastmod>2026-06-04T04:12:13.898Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/5ab80083-808f-4022-b0a0-84d83f831a31</image:loc>
      <image:title>Higgsfield AI's Cinema Studio 2.5 Brings End-to-End Production Control to AI Filmmaking</image:title>
      <image:caption>Higgsfield AI's Cinema Studio 2.5 Brings End-to-End Production Control to AI Filmmaking Higgsfield AI, the AI video generation platform behind one of the internet's fastest-growing creative communities, released Cinema Studio 2.5 in March...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Higgsfield AI's Cinema Studio 2.5 Brings End-to-End Production Control to AI Filmmaking</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-night-one-dev-rebuilt-claude-code-in-python-100k-stars-by-morning</loc>
    <lastmod>2026-06-05T16:43:28.767Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/dd47afef-f684-48fa-8d19-967ac3912879</image:loc>
      <image:title>The Night One Dev Rebuilt Claude Code in Python — 100K Stars by Morning</image:title>
      <image:caption>The Night One Dev Rebuilt Claude Code in Python — 100K Stars by Morning On the morning of March 31, 2026, the entire source code for Anthropic's Claude Code spilled onto the public internet.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>The Night One Dev Rebuilt Claude Code in Python — 100K Stars by Morning</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/openclaw-april-2026-the-boring-features-that-made-agents-real</loc>
    <lastmod>2026-06-04T04:11:30.691Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/f1d3b2d6-5ee0-48bf-a266-c83958c6508e</image:loc>
      <image:title>OpenClaw April 2026: The Boring Features That Made Agents Real</image:title>
      <image:caption>OpenClaw April 2026: The Boring Features That Made Agents Real OpenClaw spent April 2026 shipping the kind of features nobody puts on a launch banner. Task flow. Memory provenance. Channel routing. Permission profiles. Provider manifests.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>OpenClaw April 2026: The Boring Features That Made Agents Real</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/may-2026-ai-shift-governments-mandate-pre-release-testing-openai-eyes-app-free-future-claude-wins-enterprise</loc>
    <lastmod>2026-06-04T04:10:21.874Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/72ed8a9d-5fc1-482d-aafc-a5867ad903f5</image:loc>
      <image:title>May 2026 AI Shift: Governments Mandate Pre-Release Testing, OpenAI Eyes App-Free Future, Claude Wins Enterprise</image:title>
      <image:caption>In May 2026, two of the most prominent AI companies in the world — Microsoft and xAI — agreed to give government regulators early access to their models before public release, a quiet milestone that signals AI has crossed from experimental</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>May 2026 AI Shift: Governments Mandate Pre-Release Testing, OpenAI Eyes App-Free Future, Claude Wins Enterprise</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-cloud-next-26-news-and-updates-2026-05-09</loc>
    <lastmod>2026-06-04T04:10:07.138Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/3af8f506-e23f-4bbc-a0de-94b96bca2141</image:loc>
      <image:title>Google Cloud Next '26 — News and Updates — 2026-05-09</image:title>
      <image:caption>Google Cloud Next '26, held April 22, 2026, marked the moment Google stopped hedging on enterprise AI and committed fully to infrastructure-first agentics — unveiling the Gemini Enterprise Agent Platform, 8th-generation dual-chip TPUs, and</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Google Cloud Next '26 — News and Updates — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/7-major-ai-shifts-in-may-2026-government-testing-mandates-anthropic-s-200b-bet-and-the-agent-only-future</loc>
    <lastmod>2026-06-05T16:42:56.091Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/79185555-6374-47fd-9b42-18904d398f09</image:loc>
      <image:title>7 Major AI Shifts in May 2026: Government Testing Mandates, Anthropic's $200B Bet, and the Power Crisis</image:title>
      <image:caption>Anthropic has committed to a $200 billion compute infrastructure partnership with Google Cloud — and that number landed in May 2026 alongside a reported 80x surge in Claude usage, signaling that AI has crossed from product curiosity into cr</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>7 Major AI Shifts in May 2026: Government Testing Mandates, Anthropic's $200B Bet, and the Power Crisis</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-model-releases-may-2026-gpt-5-5-gemma-4-claude-grok-updates</loc>
    <lastmod>2026-06-04T04:08:48.520Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c28afd1e-e713-4c4d-b166-f9e54bea3613</image:loc>
      <image:title>AI Model Releases May 2026 — GPT-5.5, Gemma 4, Claude & Grok Updates</image:title>
      <image:caption>Claude Mythos, Anthropic's still-restricted frontier model, is benchmarking at 93.9% on SWE-bench Verified and 94.6% on GPQA Diamond — numbers that sit in a different tier from anything publicly available today.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>AI Model Releases May 2026 — GPT-5.5, Gemma 4, Claude & Grok Updates</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/openai-releases-gpt-5-5-instant-2026-05-09</loc>
    <lastmod>2026-06-04T04:08:29.112Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c334b250-2895-42e9-9cbd-08c2b948401d</image:loc>
      <image:title>OpenAI releases GPT-5.5 Instant — 2026-05-09</image:title>
      <image:caption>OpenAI swapped out GPT-5.3 Instant on May 5, 2026, replacing it with GPT-5.5 Instant as the default model powering ChatGPT for free and paid users alike. The update brings a notable jump in math reasoning — an AIME 2025 score of 81.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>OpenAI releases GPT-5.5 Instant — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/7-explosive-ai-updates-in-may-2026-that-every-founder-must-know</loc>
    <lastmod>2026-06-04T04:08:13.838Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/18f45b22-3bfa-4678-84f8-6146082dd12d</image:loc>
      <image:title>7 Explosive AI Updates in May 2026 That Every Founder Must Know</image:title>
      <image:caption>May 2026 has delivered a cluster of AI announcements significant enough to reshape how founders think about infrastructure, compliance, and distribution — not just tools.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>7 Explosive AI Updates in May 2026 That Every Founder Must Know</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-latest-artificial-intelligence-updates-2026-2026-05-09</loc>
    <lastmod>2026-06-04T04:07:41.080Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/27d147ca-2a95-4f52-917d-c520efd3aec9</image:loc>
      <image:title>AI News: Latest Artificial Intelligence Updates (2026) — 2026-05-09</image:title>
      <image:caption>The first week of March 2026 produced twelve major AI model releases — more than any comparable stretch in the industry's history — and the pace of change has made even seasoned observers recalibrate how quickly the field is moving.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>AI News: Latest Artificial Intelligence Updates (2026) — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-news-may-2026-monthly-digest-2026-05-09</loc>
    <lastmod>2026-05-18T22:25:15.102Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/0dc8b00e-a8ec-4eab-824c-bcf9bfd55b75</image:loc>
      <image:title>AI News May 2026: Monthly Digest — 2026-05-09</image:title>
      <image:caption>---</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>AI News May 2026: Monthly Digest — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-releases-new-ai-agents-to-challenge-openai-and-anthropic-2026-04-22</loc>
    <lastmod>2026-06-04T04:07:26.702Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e1d55545-b889-4b8f-ac09-9811af259d8d</image:loc>
      <image:title>Google Releases New AI Agents to Challenge OpenAI and Anthropic — 2026-04-22</image:title>
      <image:caption>Google introduced the Gemini Enterprise Agent Platform at Google Cloud Next on April 22, bringing persistent agent memory, pre-launch simulation environments, and a no-code builder into direct competition with offerings from OpenAI and Anth</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Google Releases New AI Agents to Challenge OpenAI and Anthropic — 2026-04-22</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/diving-into-spec-driven-development-with-github-spec-kit-2026-05-09</loc>
    <lastmod>2026-06-04T04:09:34.690Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/45e43c6e-d03d-40ed-9b22-a6bce2d617db</image:loc>
      <image:title>Diving Into Spec-Driven Development With GitHub Spec Kit — 2026-05-09</image:title>
      <image:caption>GitHub shipped Spec Kit in May 2026, giving developers a CLI-backed framework that forces AI coding agents to read explicit requirements before they write a single line of code.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Diving Into Spec-Driven Development With GitHub Spec Kit — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/nvidia-launches-ising-2026-05-09</loc>
    <lastmod>2026-05-18T22:23:35.366Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ec665e06-0306-4ec6-8788-71f49c6af884</image:loc>
      <image:title>NVIDIA Launches Ising — 2026-05-09</image:title>
      <image:caption>On May 9, 2026, NVIDIA released Ising — the first open-source AI model family built specifically to solve quantum computing's two most stubborn engineering problems — and within days it was already running at Harvard, Fermilab, Lawrence Ber</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>NVIDIA Launches Ising — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/toolscompare-may-2026-digest-claude-opus-4-7-200b-anthropic-google-deal-ai-chat-logs-now-legal-evidence</loc>
    <lastmod>2026-06-04T13:20:56.706Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b014d369-f73b-46cc-999d-08c8928db1e9</image:loc>
      <image:title>ToolsCompare May 2026 Digest: Claude Opus 4.7, $200B Anthropic/Google Deal, AI Chat Logs</image:title>
      <image:caption>Anthropic closed May with its largest infrastructure commitment to date: a five-year, $200 billion agreement with Google Cloud that briefly pushed Alphabet past Nvidia in market capitalization.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>ToolsCompare May 2026 Digest: Claude Opus 4.7, $200B Anthropic/Google Deal, AI Chat Logs</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/every-major-ai-model-released-in-may-2026-2026-05-09</loc>
    <lastmod>2026-06-04T04:06:14.100Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/46757717-b463-497d-9f92-22062fc4b282</image:loc>
      <image:title>Every Major AI Model Released in May 2026 — 2026-05-09</image:title>
      <image:caption>May 2026 is shaping up to be the most consequential month in AI model releases since the field took off — and it's only nine days in. Anthropic's next-generation flagship, codenamed Mythos, has leaked internal benchmark scores of 93.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Every Major AI Model Released in May 2026 — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-cloud-next-26-2026-05-09</loc>
    <lastmod>2026-06-04T04:05:51.105Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/a6a06c53-db33-46e2-bd9f-6e0ec6b1f595</image:loc>
      <image:title>Google Cloud Next '26 — 2026-05-09</image:title>
      <image:caption>Google processed 16 billion tokens per minute across its cloud infrastructure as of April 2026 — up from 10 billion just one quarter earlier — and that single number, announced at Cloud Next '26, tells you everything about the pace Google i</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>Google Cloud Next '26 — 2026-05-09</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/gpt-5-5-instant-is-now-chatgpt-s-default-here-s-the-api-change-every-developer-needs-to-know</loc>
    <lastmod>2026-05-18T22:21:54.721Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/63477c31-2bd4-49f0-9ea3-ddce74518ebd</image:loc>
      <image:title>GPT-5.5 Instant Is Now ChatGPT's Default — Here's the API Change Every Developer Needs to Know</image:title>
      <image:caption>On May 5, 2026, OpenAI quietly swapped out GPT-5.3 Instant and made GPT-5.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-09</news:publication_date>
      <news:title>GPT-5.5 Instant Is Now ChatGPT's Default — Here's the API Change Every Developer Needs to Know</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/aws-just-gave-coding-agents-a-cheat-sheet</loc>
    <lastmod>2026-05-18T22:20:14.051Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/9017c47d-26b8-4a9a-9868-3a0e0a8201ed</image:loc>
      <image:title>AWS Just Gave Coding Agents a Cheat Sheet</image:title>
      <image:caption>AWS Just Gave Coding Agents a Cheat Sheet AWS launched the Agent Toolkit for AWS (yes, the AWS Agent Toolkit) on May 6, 2026 — a free, production-ready bundle of MCP server, skills, plugins, and rules files designed to fix the two ways AI...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>AWS Just Gave Coding Agents a Cheat Sheet</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-agents-can-now-dream-anthropic-ships-cross-session-memory-curation-in-research-preview</loc>
    <lastmod>2026-06-04T04:05:35.794Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/bb30540a-9967-4760-8790-ce328e1f29bd</image:loc>
      <image:title>Claude Agents Can Now Dream: Anthropic Ships Cross-Session Memory Curation in Research Preview</image:title>
      <image:caption>Claude Agents Can Now "Dream": Anthropic Ships Cross-Session Memory Curation in Research Preview Category: AI Development Tags: Anthropic, Claude Code, Managed Agents, Memory, AI Agents Date: May 7, 2026 At its Code with Claude developer...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Claude Agents Can Now Dream: Anthropic Ships Cross-Session Memory Curation in Research Preview</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/gemma-4-mtp-drafters-make-inference-up-to-3x-faster-here-s-how-to-enable-them-in-ollama</loc>
    <lastmod>2026-06-04T04:25:25.180Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/07323c4e-60e2-4acc-af59-2f3f20d7236c</image:loc>
      <image:title>Gemma 4 MTP Drafters Make Inference Up to 3x Faster — Here's How to Enable Them in Ollama</image:title>
      <image:caption>Gemma 4 MTP Drafters Make Inference Up to 3x Faster — Here's How to Enable Them in Ollama On May 5, 2026, Google released a set of Multi-Token Prediction (MTP) drafters for the Gemma 4 family that promise up to a 3x speedup on local...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Gemma 4 MTP Drafters Make Inference Up to 3x Faster — Here's How to Enable Them in Ollama</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ltx-video-2-3-v1-1-is-the-best-open-source-video-model-yet-and-it-runs-on-8-gb-vram</loc>
    <lastmod>2026-06-04T04:04:52.142Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b2d07a30-0f96-44e6-b567-09dacc596cf7</image:loc>
      <image:title>LTX Video 2.3 v1.1 Is the Best Open-Source Video Model Yet — And It Runs on 8 GB VRAM</image:title>
      <image:caption>LTX Video 2.3 v1.1 Is the Best Open-Source Video Model Yet — And It Runs on 8 GB VRAM Lightricks quietly pushed an update to its 22-billion-parameter LTX-2.3 video model in mid-April, and the gap between it and the original 2.3 release is...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>LTX Video 2.3 v1.1 Is the Best Open-Source Video Model Yet — And It Runs on 8 GB VRAM</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/hermes-workspace-is-the-free-open-source-ai-agent-hq-nobody-s-talking-about-the-conductor-changes-everything</loc>
    <lastmod>2026-06-04T04:04:38.403Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/8bd929f4-bfea-491c-a26f-aae351cb1cef</image:loc>
      <image:title>Hermes Workspace Is the Free Open-Source AI Agent HQ Nobody's Talking About — The Conductor Changes Everything</image:title>
      <image:caption>Hermes Workspace Is the Free Open-Source AI Agent HQ Nobody's Talking About — The Conductor Changes Everything Most people running an AI agent today are running one agent on one task. It works, you wait, you start the next thing.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Hermes Workspace Is the Free Open-Source AI Agent HQ Nobody's Talking About — The Conductor Changes Everything</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/stripe-s-projects-dev-lets-ai-agents-sign-up-for-services-without-a-browser</loc>
    <lastmod>2026-05-18T22:13:38.778Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/2d6a3832-db02-43fe-9e91-a2260d34ee20</image:loc>
      <image:title>Stripe's projects.dev Lets AI Agents Sign Up for Services Without a Browser</image:title>
      <image:caption>Stripe's projects.dev CLI plugin lets AI agents provision databases, hosting, and auth without browser signups — using Stripe's KYC as a shared trust layer.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Stripe's projects.dev Lets AI Agents Sign Up for Services Without a Browser</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/how-to-build-an-efficient-knowledge-base-for-ai-models-2026-05-07</loc>
    <lastmod>2026-06-04T04:04:07.421Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/0f8aab61-e323-4c5b-aa09-4e7fa12c5b3b</image:loc>
      <image:title>How to Build an Efficient Knowledge Base for AI Models — 2026-05-07</image:title>
      <image:caption>Building a retrieval-augmented generation system that actually works in production remains one of the harder unsolved problems in applied AI — and a new detailed framework published on Towards Data Science by Nidhin Karunakaran Ponon on May</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>How to Build an Efficient Knowledge Base for AI Models — 2026-05-07</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/provision-infrastructure-with-one-cli-stripe-projects-goes-ga-with-32-providers</loc>
    <lastmod>2026-06-04T04:03:52.096Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/52d3fef7-b518-48fb-87dc-2dd3e47aa538</image:loc>
      <image:title>Provision Infrastructure with One CLI: Stripe Projects Goes GA With 32 Providers</image:title>
      <image:caption>Provision Infrastructure with One CLI: Stripe Projects Goes GA With 32 Providers Stripe Projects exited developer preview and reached general availability with 14 new partners (32 total), letting you — or your AI coding agent — provision a...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Provision Infrastructure with One CLI: Stripe Projects Goes GA With 32 Providers</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropic-reports-80x-q1-growth-spacex-compute-deal-and-autonomous-multi-agent-upgrades-at-claude-code-developer-conference</loc>
    <lastmod>2026-06-04T04:03:15.421Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/f978a39f-d65f-4b42-b7de-14414b10a4f3</image:loc>
      <image:title>Anthropic Reports 80x Q1 Growth, SpaceX Compute Deal, and Autonomous Multi-Agent Upgrades at Claude Code Developer Conference</image:title>
      <image:caption>Anthropic revealed 80x growth in both revenue and users during Q1 2026 — an 8,000% increase — at its Claude Code Developer Conference held in San Francisco, while simultaneously announcing a compute infrastructure deal with SpaceX and new c</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Anthropic Reports 80x Q1 Growth, SpaceX Compute Deal, and Autonomous Multi-Agent Upgrades at Claude Code Developer Conference</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/3-ways-to-build-interactive-web-experiences-with-gemini-2026-05-07</loc>
    <lastmod>2026-06-04T04:02:56.969Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/7d5f31e8-7eec-4bb9-833f-d51dda44fecc</image:loc>
      <image:title>3 Ways to Build Interactive Web Experiences with Gemini — 2026-05-07</image:title>
      <image:caption>Google published three community-built demos this week showing developers using Gemini 3.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>3 Ways to Build Interactive Web Experiences with Gemini — 2026-05-07</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/here-s-how-the-new-microsoft-and-openai-deal-breaks-down-2026-05-07</loc>
    <lastmod>2026-06-04T04:02:42.910Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/547a72e4-ef96-44e5-bcd7-637c749050f9</image:loc>
      <image:title>Here's How the New Microsoft and OpenAI Deal Breaks Down — 2026-05-07</image:title>
      <image:caption>Microsoft and OpenAI restructured their foundational partnership in late April 2026, ending Azure's exclusive lock on OpenAI model distribution — and within 24 hours, OpenAI had already announced it was bringing its models and Codex to Amaz</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Here's How the New Microsoft and OpenAI Deal Breaks Down — 2026-05-07</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/stripe-just-solved-one-of-ai-agents-biggest-problems</loc>
    <lastmod>2026-06-04T04:02:23.807Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/af593093-ce61-4377-b55b-dc63c66b45db</image:loc>
      <image:title>Stripe Just Solved One of AI Agents' Biggest Problems</image:title>
      <image:caption>Stripe Just Solved One of AI Agents' Biggest Problems On April 30, 2026, Stripe shipped an open beta of Stripe Projects — a CLI tool that lets AI agents discover, sign up for, and pay for cloud services without a human ever opening a...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Stripe Just Solved One of AI Agents' Biggest Problems</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-s-gemini-agentic-push-transforms-workspace-into-a-no-code-automation-engine</loc>
    <lastmod>2026-06-04T04:02:07.916Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/96f0cecc-36cd-40e6-a44b-0760cb23c0b6</image:loc>
      <image:title>Google's Gemini Agentic Push Transforms Workspace Into a No-Code Automation Engine</image:title>
      <image:caption>Google's Gemini Agentic Push Transforms Workspace Into a No-Code Automation Engine Google has crossed a threshold most enterprise software companies only promise: it has embedded AI deeply enough into its productivity suite that routine...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Google's Gemini Agentic Push Transforms Workspace Into a No-Code Automation Engine</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-gemini-s-workspace-overhaul-makes-manual-data-entry-obsolete</loc>
    <lastmod>2026-06-04T04:01:53.240Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e7fcc63d-a002-4db8-8991-c098e96e370a</image:loc>
      <image:title>Google Gemini's Workspace Overhaul Makes Manual Data Entry Obsolete</image:title>
      <image:caption>Google Gemini's Workspace Overhaul Makes Manual Data Entry Obsolete Google has spent the past six months systematically embedding its Gemini AI into every layer of Google Workspace — and the result is a suite of features designed to...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>Google Gemini's Workspace Overhaul Makes Manual Data Entry Obsolete</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/nvidia-lyra-2-0-generates-explorable-3d-worlds-from-a-single-photo-without-breaking-at-the-edges</loc>
    <lastmod>2026-06-04T04:01:37.601Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/cd4b324b-fd47-4313-b0e4-d3c9c01e0242</image:loc>
      <image:title>NVIDIA Lyra 2.0 Generates Explorable 3D Worlds from a Single Photo — Without Breaking at the Edges</image:title>
      <image:caption>NVIDIA Lyra 2.0 Generates Explorable 3D Worlds from a Single Photo — Without Breaking at the Edges NVIDIA Research released Lyra 2.0 on April 16, 2026, a generative AI system capable of transforming a single still image into a fully...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-07</news:publication_date>
      <news:title>NVIDIA Lyra 2.0 Generates Explorable 3D Worlds from a Single Photo — Without Breaking at the Edges</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-model-releases-tracker-2026-05-03</loc>
    <lastmod>2026-06-04T04:01:17.599Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c4d5f406-2b8f-464b-808d-e1cddeaf741b</image:loc>
      <image:title>AI Model Releases Tracker — 2026-05-03</image:title>
      <image:caption>DeepInfra is now the cheapest inference provider tracked by LLM Stats, offering input pricing as low as $0.01 per million tokens with a 10 million token context window — a floor that undercuts every other provider in the platform's catalog...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-03</news:publication_date>
      <news:title>AI Model Releases Tracker — 2026-05-03</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/llm-news-today-2026-05-03</loc>
    <lastmod>2026-05-18T22:05:43.872Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/7faa754b-cd61-44ed-b914-44cbd3da303d</image:loc>
      <image:title>LLM News Today — 2026-05-03</image:title>
      <image:caption>Microsoft quietly inserted a Co-Authored-by: GitHub Copilot line into Git commits made inside VS Code — even on machines where every AI feature had been explicitly disabled.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-03</news:publication_date>
      <news:title>LLM News Today — 2026-05-03</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-model-releases-llm-updates-tracker-2026-05-03</loc>
    <lastmod>2026-06-04T04:01:02.822Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/a8235e24-bea6-42bd-855d-ea6f8bcb3fb1</image:loc>
      <image:title>AI Model Releases & LLM Updates Tracker — 2026-05-03</image:title>
      <image:caption>Anthropic added Claude Mythos Preview to its API lineup at $2,500 per million tokens this week, making it the most expensive model the company has ever shipped — and the late-April 2026 release wave didn't stop there.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-03</news:publication_date>
      <news:title>AI Model Releases & LLM Updates Tracker — 2026-05-03</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/microsoft-embeds-a-dedicated-legal-agent-in-word-built-on-robin-ai-s-ashes-and-backed-by-anthropic</loc>
    <lastmod>2026-06-04T03:59:18.901Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/85b157e5-aaf9-4828-a744-a9099b154911</image:loc>
      <image:title>Microsoft Embeds a Dedicated Legal Agent in Word, Built on Robin AI's Ashes and Backed by Anthropic</image:title>
      <image:caption>Microsoft on April 30, 2026, launched the Legal Agent in Microsoft Word — a purpose-built AI agent designed specifically for legal professionals to review contracts, generate redlines, and enforce internal playbooks, all natively inside the application where the overwhelming majo</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-03</news:publication_date>
      <news:title>Microsoft Embeds a Dedicated Legal Agent in Word, Built on Robin AI's Ashes and Backed by Anthropic</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/fine-tuning-llms-for-specialized-agents-why-prompts-aren-t-enough-2026-05-02</loc>
    <lastmod>2026-06-11T15:42:27.887Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/66639cac-e750-4754-9e01-f00f48f994d8</image:loc>
      <image:title>Fine-Tuning LLMs for Specialized Agents — Why Prompts Aren't Enough — 2026-05-02</image:title>
      <image:caption>As AI agents take on increasingly specialized roles — enforcing rigid output formats, maintaining brand voice, or staying in character across thousands of interactions — developers are discovering that crafting better prompts can only take them so far. The case for fine-tuning la</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-02</news:publication_date>
      <news:title>Fine-Tuning LLMs for Specialized Agents — Why Prompts Aren't Enough — 2026-05-02</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/read-amazon-s-6-internal-tenets-for-ai-adoption-cutting-edge-not-bleeding-edge</loc>
    <lastmod>2026-06-04T13:07:03.764Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/483b3da1-cc3f-46c5-a1ae-86f386232173</image:loc>
      <image:title>Read Amazon's 6 internal tenets for AI adoption: 'Cutting edge, not bleeding edge'</image:title>
      <image:caption>Amazon's retail engineering division has quietly formalized how its thousands of internal teams should build with artificial intelligence — and the rules push back hard against the upgrade-chasing, AI-everywhere instincts that have come to define the industry's current moment. Si</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Read Amazon's 6 internal tenets for AI adoption: 'Cutting edge, not bleeding edge'</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/openai-codex-vs-claude-code-6-features-compared-2026</loc>
    <lastmod>2026-06-04T04:29:47.029Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/d49f096b-a1d2-4de6-843a-5e060eb48d60</image:loc>
      <image:title>OpenAI Codex vs Claude Code: 6 Features Compared (2026)</image:title>
      <image:caption>April 2026: OpenAI Codex vs Claude Code across 6 features — computer use, parallel agents, image gen, memory, plugins, scheduling. Verdict: tied 3-3.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>OpenAI Codex vs Claude Code: 6 Features Compared (2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/horizons-vs-lovable-vs-claude-code-best-for-utility-sites</loc>
    <lastmod>2026-06-04T04:29:32.683Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/36792d6e-5143-4198-918f-4ad22239ef34</image:loc>
      <image:title>Horizons vs Lovable vs Claude Code: Best for Utility Sites?</image:title>
      <image:caption>Horizons vs Lovable vs Claude Code: Best for Utility Sites? You want to build a monetizable utility website — a tool that does one thing well, ranks on Google, and earns via AdSense or affiliate links.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Horizons vs Lovable vs Claude Code: Best for Utility Sites?</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-design-vs-jitter-vs-rive-for-ui-animation-2026</loc>
    <lastmod>2026-06-04T04:28:28.017Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/19cb5c69-e696-4cfb-ae3c-6814a9c215b7</image:loc>
      <image:title>Claude Design vs Jitter vs Rive for UI Animation (2026)</image:title>
      <image:caption>Claude Design vs Jitter vs Rive for UI Animation (2026) If you are a no-code designer who wants to ship animated UI today, three tools dominate the conversation in April 2026: Claude Design (Anthropic's prompt-to-prototype product), Jitter...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Claude Design vs Jitter vs Rive for UI Animation (2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/vs-code-copilot-customization-vs-claude-code-5-primitives-compared-2026</loc>
    <lastmod>2026-06-05T16:46:25.485Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/6479575f-330c-4da0-87f6-951c6ad2df83</image:loc>
      <image:title>VS Code Copilot Customization vs Claude Code: 5 Primitives Compared (2026)</image:title>
      <image:caption>VS Code Copilot Customization vs Claude Code: 5 Primitives Compared (2026) In April 2026, VS Code shipped a unified Chat Customizations editor that surfaces five customization primitives in one place: custom agents, agent skills, custom...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>VS Code Copilot Customization vs Claude Code: 5 Primitives Compared (2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/zapier-sdk-vs-mcp-picking-the-right-bridge-for-claude-in-2026</loc>
    <lastmod>2026-05-18T23:13:03.273Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ab65ea0e-afdd-445c-b8ce-0bf6bcd39d45</image:loc>
      <image:title>Zapier SDK vs MCP: Picking the Right Bridge for Claude in 2026</image:title>
      <image:caption>Zapier SDK vs MCP: Picking the Right Bridge for Claude in 2026 Zapier ships two ways to plug Claude into 9,000+ apps, and they look superficially similar from a product-page distance. They are not.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Zapier SDK vs MCP: Picking the Right Bridge for Claude in 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-50-ai-stack-claude-pro-wispr-flow-and-manus-for-business-owners</loc>
    <lastmod>2026-05-18T21:57:13.972Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/96024d31-72ec-4db2-ad39-f209c0f69804</image:loc>
      <image:title>The $50 AI Stack: Claude Pro, Wispr Flow, and Manus for Business Owners</image:title>
      <image:caption>A budget AI stack for business owners — Claude Pro for reasoning, Wispr Flow for voice, and Manus for autonomous task execution — at $49/month annually or $55 monthly. Verified prices, honest tradeoffs, and where each tool fits.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>The $50 AI Stack: Claude Pro, Wispr Flow, and Manus for Business Owners</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-ai-studio-gets-prompt-autocomplete-in-build-mode-what-it-means-for-app-builders</loc>
    <lastmod>2026-05-18T23:12:38.462Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/8db32f81-df58-4dd2-a366-51e4d18baad9</image:loc>
      <image:title>Google AI Studio Gets Prompt Autocomplete in Build Mode — What It Means for App Builders</image:title>
      <image:caption>Google AI Studio Build mode now offers prompt autocomplete: type a partial app idea, press Tab, and Gemini finishes the spec. Demo, comparisons, when to use it.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Google AI Studio Gets Prompt Autocomplete in Build Mode — What It Means for App Builders</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-s-design-the-open-standard-for-on-brand-ai-generated-ui-components</loc>
    <lastmod>2026-05-18T21:56:22.687Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/2851f73f-3131-4573-917f-814928b938c0</image:loc>
      <image:title>Google's Design — The Open Standard for On-Brand AI-Generated UI Components</image:title>
      <image:caption>Google's Design.MD — The Open Standard for On-Brand AI-Generated UI Components Source Attribution: YouTube roundup [China's Free AI Just Embarrassed Claude And ChatGPT (+12 AI Updates)](https://www.youtube.com/watch?v=Q8DoGJ0VuEI)...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Google's Design — The Open Standard for On-Brand AI-Generated UI Components</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/how-to-ship-a-vibe-coded-app-on-the-ios-app-store-after-apple-s-crackdown</loc>
    <lastmod>2026-06-04T04:28:58.308Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/de600371-7533-42e2-a7bc-58d1d843cc81</image:loc>
      <image:title>How to Ship a Vibe-Coded App on the iOS App Store (After Apple's Crackdown)</image:title>
      <image:caption>In March 2026, App Store submissions surged 84% in a single quarter — almost entirely driven by vibe-coded apps. Apple responded by enforcing rules that were already on the books but rarely applied at</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>How to Ship a Vibe-Coded App on the iOS App Store (After Apple's Crackdown)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-ai-power-shift-cursor-s-60b-bet-the-saaspocalypse-and-openai-s-exodus-explained</loc>
    <lastmod>2026-06-04T03:58:00.781Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/dc52df26-d7ab-471c-b2b7-0754fb27f6e5</image:loc>
      <image:title>The AI Power Shift: Cursor's $60B Bet, the SaaSpocalypse, and OpenAI's Exodus Explained</image:title>
      <image:caption>SpaceX announced a deal giving it the right to **acquire Cursor for $60 billion**, or pay $10 billion for Cursor's work if the acquisition does not close. Cursor, built by Anysphere (four MIT classmat</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>The AI Power Shift: Cursor's $60B Bet, the SaaSpocalypse, and OpenAI's Exodus Explained</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/grok-s-multimodal-expansion-in-2026-what-s-real-and-what-s-rumored</loc>
    <lastmod>2026-06-04T03:57:44.845Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/567fc84a-0688-41bb-94ad-e5ad6439d27c</image:loc>
      <image:title>Grok's Multimodal Expansion in 2026 — What's Real and What's Rumored</image:title>
      <image:caption>Grok's Multimodal Expansion in 2026 — What's Real and What's Rumored A YouTube roundup from April 26, 2026 claimed that Grok had released a new version (referenced as "4.3") with video input and real file output capabilities (PowerPoint,...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Grok's Multimodal Expansion in 2026 — What's Real and What's Rumored</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/chatgpt-images-2-0-five-practical-use-cases-you-can-ship-this-week</loc>
    <lastmod>2026-05-18T21:54:12.018Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/f3663f5f-b527-42ca-8ae4-cedf82d03d24</image:loc>
      <image:title>ChatGPT Images 2.0 — Five Practical Use Cases You Can Ship This Week</image:title>
      <image:caption>ChatGPT Images 2.0 — Five Practical Use Cases You Can Ship This Week OpenAI shipped ChatGPT Images 2.0 on April 21, 2026, and within 48 hours it became the top-rated image model on the LMArena image leaderboard.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>ChatGPT Images 2.0 — Five Practical Use Cases You Can Ship This Week</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/chatgpt-agents-for-slack-and-linear-autonomous-teammates-in-your-workspace-april-2026</loc>
    <lastmod>2026-06-04T04:00:04.980Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/8e443ea5-64ab-4413-b61c-2044c7eb65d8</image:loc>
      <image:title>ChatGPT Agents for Slack and Linear — Autonomous Teammates in Your Workspace (April 2026)</image:title>
      <image:caption>ChatGPT Agents for Slack and Linear — Autonomous Teammates in Your Workspace (April 2026) OpenAI shipped expanded ChatGPT agent capabilities for workplace tools in April 2026, enabling autonomous AI teammates that can live natively in...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>ChatGPT Agents for Slack and Linear — Autonomous Teammates in Your Workspace (April 2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/multica-vs-claude-routines-vs-claude-managed-agents-self-hosted-ai-orchestration-compared-2026</loc>
    <lastmod>2026-06-04T04:27:14.924Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/0328e53c-8820-4502-9bba-92e018ca2433</image:loc>
      <image:title>Multica vs Claude Routines vs Claude Managed Agents — Self-Hosted AI Orchestration Compared (2026)</image:title>
      <image:caption>Multica vs Claude Routines vs Claude Managed Agents — Self-Hosted AI Orchestration Compared (2026) Three spring-2026 products promise the same dream: hand a coding agent a task, walk away, return to a finished pull request.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-05-01</news:publication_date>
      <news:title>Multica vs Claude Routines vs Claude Managed Agents — Self-Hosted AI Orchestration Compared (2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-code-open-sourced-new-veo-model-wan-2-7-glm-5v-qwen-new-model-huge-ai</loc>
    <lastmod>2026-06-04T03:56:48.026Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/7e382626-e888-4ef3-b74b-8eaa3ae5aee2</image:loc>
      <image:title>Claude Code Open Sourced, New Veo Model, Wan 2.7, GLM-5V, Qwen New Model — HUGE AI</image:title>
      <image:caption>A single week in April delivered an unusual concentration of open-source releases, leaked source code, and competitive video-generation benchmarks — enough to shift developer conversations across multiple domains simultaneously.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-30</news:publication_date>
      <news:title>Claude Code Open Sourced, New Veo Model, Wan 2.7, GLM-5V, Qwen New Model — HUGE AI</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-sycophancy-problem-in-large-language-models-jinal-desai-feb-2026</loc>
    <lastmod>2026-06-04T03:59:49.141Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/024fb84f-7e6a-4d64-9c02-22c5663b5438</image:loc>
      <image:title>The Sycophancy Problem in Large Language Models (Jinal Desai, Feb 2026)</image:title>
      <image:caption>A new whitepaper published in February 2026 by researcher Jinal Desai puts a hard number on something many developers have long suspected: between 58 and 63 percent of responses generated by leading large language models are sycophantic, me</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-30</news:publication_date>
      <news:title>The Sycophancy Problem in Large Language Models (Jinal Desai, Feb 2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/autoclaw-by-autoglm</loc>
    <lastmod>2026-06-04T03:16:59.685Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/6350c31d-0a97-4dac-b954-dc0863400cc6</image:loc>
      <image:title>AutoClaw by AutoGLM</image:title>
      <image:caption>AutoGLM, the team behind the GLM family of large language models from Chinese AI lab Zhipu AI, has announced AutoClaw, a desktop application that embeds an AI task agent directly inside enterprise instant messaging platforms.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-30</news:publication_date>
      <news:title>AutoClaw by AutoGLM</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/agentic-platform-engineering-with-github-copilot</loc>
    <lastmod>2026-06-04T03:56:04.442Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/7cb59ace-4c86-4a56-99fa-e95b68d3683f</image:loc>
      <image:title>Agentic Platform Engineering with GitHub Copilot</image:title>
      <image:caption>Microsoft is extending GitHub Copilot beyond code completion into a full operational layer for platform teams, introducing a structured framework that uses AI agents to encode institutional knowledge, enforce infrastructure standards, and a</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-30</news:publication_date>
      <news:title>Agentic Platform Engineering with GitHub Copilot</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-code-is-now-the-world-s-1-design-tool-2026-04-25</loc>
    <lastmod>2026-06-04T03:55:50.984Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/32a2093e-ec8c-46d9-beb1-de517038142d</image:loc>
      <image:title>Claude Code Is Now the World's #1 Design Tool — 2026-04-25</image:title>
      <image:caption>A GitHub repository showing how to use Claude Code as a full-stack design tool crossed 50,000 stars in under two weeks, signaling a shift in how developers think about AI-assisted visual output.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-30</news:publication_date>
      <news:title>Claude Code Is Now the World's #1 Design Tool — 2026-04-25</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/vs-code-ships-unified-chat-customizations-ui-for-github-copilot-agents-skills-hooks-in-one-place</loc>
    <lastmod>2026-05-18T21:47:22.273Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/dd7074a7-dfdb-49a2-b617-c1f1ca6ebee0</image:loc>
      <image:title>VS Code Ships Unified Chat Customizations UI for GitHub Copilot — Agents, Skills, Hooks in One Place</image:title>
      <image:caption>Microsoft has consolidated GitHub Copilot's growing set of personalization features into a single interface inside VS Code, giving developers a unified control surface for the AI coding assistant's most powerful customization primitives.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-30</news:publication_date>
      <news:title>VS Code Ships Unified Chat Customizations UI for GitHub Copilot — Agents, Skills, Hooks in One Place</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/moss-audio-openmoss-open-source-audio-foundation-model</loc>
    <lastmod>2026-05-18T21:43:07.795Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/dc768bbd-70e7-4bb9-8649-c569ddbc0aed</image:loc>
      <image:title>MOSS-Audio — OpenMOSS Open-Source Audio Foundation Model</image:title>
      <image:caption>OpenMOSS released MOSS-Audio, a unified open-source foundation model that handles speech transcription, speaker/emotion analysis, environmental sound, music understanding, audio QA, and time-ground...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-29</news:publication_date>
      <news:title>MOSS-Audio — OpenMOSS Open-Source Audio Foundation Model</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-for-creative-work-anthropic-apr-28-2026</loc>
    <lastmod>2026-06-04T03:55:11.121Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/abd38648-2a36-4e3a-a09f-3a0958ff4c12</image:loc>
      <image:title>Claude for Creative Work — Anthropic (Apr 28, 2026)</image:title>
      <image:caption>Anthropic is launching a coalition of MCP-based connectors for major creative tools (Blender, Adobe CC, Autodesk Fusion, Ableton, Splice, Affinity, SketchUp, Resolume Arena), plus Claude Design — a...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-29</news:publication_date>
      <news:title>Claude for Creative Work — Anthropic (Apr 28, 2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/building-the-agentic-cloud-everything-we-launched-during-agents-week-2026</loc>
    <lastmod>2026-06-04T03:54:09.806Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/42663357-6f85-494c-803d-bc1eef4aa2f5</image:loc>
      <image:title>Building the agentic cloud: everything we launched during Agents Week 2026</image:title>
      <image:caption>Cloudflare Agents Week 2026 — Key Learnings</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>Building the agentic cloud: everything we launched during Agents Week 2026</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/3-biohacks-high-performing-entrepreneurs-are-using-to-outlast-burnout</loc>
    <lastmod>2026-05-18T21:41:47.816Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/8500e5f9-f338-4777-b80b-692abf65a677</image:loc>
      <image:title>3 Biohacks High-Performing Entrepreneurs Are Using to Outlast Burnout</image:title>
      <image:caption>73% of startup executives are experiencing "shadow burnout" — performing at high levels while silently degrading cognitively. The article introduces the **Superhuman Protocol**: a 15–20 minute dail...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>3 Biohacks High-Performing Entrepreneurs Are Using to Outlast Burnout</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/agents-that-remember-introducing-cloudflare-agent-memory-apr-17-2026</loc>
    <lastmod>2026-06-04T03:53:29.030Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/a1e2e11c-86c0-4453-9b4a-07a0a657ea5e</image:loc>
      <image:title>Agents that Remember — Introducing Cloudflare Agent Memory (Apr 17, 2026)</image:title>
      <image:caption>Cloudflare launched a private beta of **Agent Memory** — a managed service that extracts, classifies, deduplicates, and retrieves knowledge from agent conversations. The architecture solves "contex...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>Agents that Remember — Introducing Cloudflare Agent Memory (Apr 17, 2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-design-everything-you-can-build-in-16-minutes-5-real-use-cases</loc>
    <lastmod>2026-06-04T03:52:52.343Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e243ea68-f8b8-4b65-ab90-6dde31e76295</image:loc>
      <image:title>Claude Design — Everything You Can Build in 16 Minutes (5 Real Use Cases)</image:title>
      <image:caption>Claude Design generates animated videos, interactive slide decks, landing page clones, 3D effects, mobile app prototypes, and full design systems — all as live HTML artifacts. The key thesis: code ...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>Claude Design — Everything You Can Build in 16 Minutes (5 Real Use Cases)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/5-useful-things-i-do-with-a-local-llm-on-my-phone</loc>
    <lastmod>2026-06-04T03:52:17.556Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e22a9f51-271d-4efc-9021-3aba1fff652c</image:loc>
      <image:title>5 Useful Things I Do With a Local LLM on My Phone</image:title>
      <image:caption>Running a small language model locally on an Android phone (specifically MNN Chat by Alibaba) unlocks five practical use cases that cloud AI handles poorly: private thinking partnerships, messy-not...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>5 Useful Things I Do With a Local LLM on My Phone</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/cowork-on-3p-how-to-run-any-llm-in-claude-cowork-and-claude-code</loc>
    <lastmod>2026-05-18T21:40:01.038Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/0af47c00-5c0e-4e41-8022-2d7a07467437</image:loc>
      <image:title>Cowork on 3P — How to Run Any LLM in Claude Cowork and Claude Code</image:title>
      <image:caption>Anthropic quietly shipped third-party inference for Claude Desktop — you can now run Cowork and Code against OpenRouter, Bedrock, Vertex, Foundry, or a local model proxy, with the same skill/plugin...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>Cowork on 3P — How to Run Any LLM in Claude Cowork and Claude Code</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/intuit-s-financial-intelligence-apps-are-now-available-in-claude</loc>
    <lastmod>2026-06-04T03:50:42.729Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/dcbfefba-adda-4168-82a1-a67ca25ff569</image:loc>
      <image:title>Intuit's Financial Intelligence Apps Are Now Available in Claude</image:title>
      <image:caption>Intuit has launched TurboTax, Credit Karma, QuickBooks, Mailchimp, and Intuit Enterprise Suite as integrations within Claude — the first major enterprise financial suite to embed directly in an LLM...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>Intuit's Financial Intelligence Apps Are Now Available in Claude</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-deepmind-introduces-vision-banana-marktechpost-apr-25-2026</loc>
    <lastmod>2026-06-04T03:54:38.800Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e11d070a-21e3-4ed3-ab34-e7f026913d6e</image:loc>
      <image:title>Google DeepMind Introduces Vision Banana (MarkTechPost, Apr 25 2026)</image:title>
      <image:caption>Google DeepMind published "Image Generators are Generalist Vision Learners" (arXiv:2604.20329, Apr 22 2026), introducing **Vision Banana** — a single model built by instruction-tuning their state-o...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>Google DeepMind Introduces Vision Banana (MarkTechPost, Apr 25 2026)</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-debugging-wars-cursor-3-takes-aim-at-claude-code-s-agentic-edge</loc>
    <lastmod>2026-06-04T03:49:10.542Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/d89da2b0-cbbf-4b6b-9fd9-58aa995490ae</image:loc>
      <image:title>The Debugging Wars — Cursor 3 Takes Aim at Claude Code's Agentic Edge</image:title>
      <image:caption>Cursor 3 shipped an **Agents Window** — a persistent, multi-agent orchestration layer inside the IDE — positioning it as a direct competitor to Claude Code's terminal-first agentic workflow. The pi...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>The Debugging Wars — Cursor 3 Takes Aim at Claude Code's Agentic Edge</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-vercel-ai-breach-what-developers-need-to-know-and-do-now</loc>
    <lastmod>2026-06-04T03:50:27.828Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b7744367-a7ee-461d-8e3b-1e7c1265ea5a</image:loc>
      <image:title>The Vercel AI Breach: What Developers Need to Know and Do Now</image:title>
      <image:caption>Vercel disclosed a security breach on April 19, 2026. Environment variables were exposed via a compromised third-party AI tool. Here is what was affected and what to do.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-28</news:publication_date>
      <news:title>The Vercel AI Breach: What Developers Need to Know and Do Now</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/alibaba-unveils-generative-ai-model-capable-of-transforming-text-into-3d-environments</loc>
    <lastmod>2026-06-04T03:47:46.967Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/97abb4d1-0315-485e-afec-e46dc5311da7</image:loc>
      <image:title>Alibaba Unveils Generative AI Model Capable of Transforming Text into 3D Environments</image:title>
      <image:caption>Alibaba Unveils Generative AI Model Capable of Transforming Text into 3D Environments Alibaba has announced a significant breakthrough in generative artificial intelligence with the introduction of a new model designed to synthesize...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>Alibaba Unveils Generative AI Model Capable of Transforming Text into 3D Environments</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/malaysia-emerges-as-a-strategic-hub-for-nvidia-s-ai-infrastructure-expansion</loc>
    <lastmod>2026-05-18T21:08:10.352Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/8a7eb4f5-be66-42e8-aa35-c4ce87d1f972</image:loc>
      <image:title>Malaysia Emerges as a Strategic Hub for NVIDIA’s AI Infrastructure Expansion</image:title>
      <image:caption>Malaysia Emerges as a Strategic Hub for NVIDIA’s AI Infrastructure Expansion NVIDIA is significantly expanding its footprint in Malaysia, partnering with local entities and the Malaysian government to develop a robust ecosystem for...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>Malaysia Emerges as a Strategic Hub for NVIDIA’s AI Infrastructure Expansion</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-autonomy-tax-why-the-shift-to-ai-agents-is-driving-exponential-compute-costs</loc>
    <lastmod>2026-06-04T03:47:27.746Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/59e7135d-22ca-4925-afe1-1af17bdccff2</image:loc>
      <image:title>The Autonomy Tax: Why the Shift to AI Agents is Driving Exponential Compute Costs</image:title>
      <image:caption>The Autonomy Tax: Why the Shift to AI Agents is Driving Exponential Compute Costs As the artificial intelligence industry transitions from simple, single-turn chat interfaces to autonomous agents capable of executing complex, multi-step...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>The Autonomy Tax: Why the Shift to AI Agents is Driving Exponential Compute Costs</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-openclaw-illusion-why-the-latest-ai-darling-fails-the-developer-litmus-test</loc>
    <lastmod>2026-06-05T23:30:07.115Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/86e514ed-9b15-40cf-ae07-7af4428e209a</image:loc>
      <image:title>The OpenClaw Illusion: Why the Latest AI Darling Fails the Developer Litmus Test</image:title>
      <image:caption>The OpenClaw Illusion: Why the Latest AI Darling Fails the Developer Litmus Test As OpenClaw gains significant traction in the AI-driven development space, a growing wave of skepticism is emerging among engineers and software architects.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>The OpenClaw Illusion: Why the Latest AI Darling Fails the Developer Litmus Test</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-leverages-gemini-to-enable-natural-language-vibe-coding-for-webxr</loc>
    <lastmod>2026-06-04T03:46:45.520Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e91d41a4-2b96-48cd-aab2-c5b3aed1ac54</image:loc>
      <image:title>Google Leverages Gemini to Enable Natural Language "Vibe Coding" for WebXR</image:title>
      <image:caption>Google Leverages Gemini to Enable Natural Language "Vibe Coding" for WebXR Google is introducing a new Gemini-powered extension designed to streamline WebXR development through natural language processing.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>Google Leverages Gemini to Enable Natural Language "Vibe Coding" for WebXR</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-expands-gemini-cli-with-subagent-orchestration-for-complex-workers</loc>
    <lastmod>2026-05-18T21:16:28.563Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/a0ac695a-5aac-4d5f-a0a5-2685b216f1d6</image:loc>
      <image:title>Google Expands Gemini CLI with Subagent Orchestration for Complex Workers</image:title>
      <image:caption>Google Expands Gemini CLI with Subagent Orchestration for Complex Workers Google has announced a significant architectural update to the Gemini CLI, introducing "subagents"—specialized, modular AI instances designed to operate under the...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>Google Expands Gemini CLI with Subagent Orchestration for Complex Workers</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-velocity-gap-why-ai-driven-development-demands-a-revolution-in-platform-engineering</loc>
    <lastmod>2026-06-04T03:45:41.997Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/c14d7f3d-3e7e-4981-8f98-6a9c644cd70a</image:loc>
      <image:title>The Velocity Gap: Why AI-Driven Development Demands a Revolution in Platform Engineering</image:title>
      <image:caption>The Velocity Gap: Why AI-Driven Development Demands a Revolution in Platform Engineering As Large Language Models (LLMs) and AI coding assistants fundamentally alter the software development lifecycle, a critical bottleneck is emerging:...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>The Velocity Gap: Why AI-Driven Development Demands a Revolution in Platform Engineering</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropic-s-claude-code-redesign-brings-agentic-power-to-the-desktop</loc>
    <lastmod>2026-06-04T03:45:25.020Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/4d613ed3-3ec5-4876-86e1-d76aca33b00f</image:loc>
      <image:title>Anthropic’s Claude Code Redesign Brings Agentic Power to the Desktop</image:title>
      <image:caption>Anthropic’s Claude Code Redesign Brings Agentic Power to the Desktop Anthropic has unveiled a significant redesign of its Claude Code desktop application, transitioning the tool from a command-line interface (CLI) utility toward a more...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>Anthropic’s Claude Code Redesign Brings Agentic Power to the Desktop</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/nvidia-launches-ising-world-s-first-open-quantum-ai-models</loc>
    <lastmod>2026-05-18T21:04:16.681Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b10aeb65-c086-405f-9044-ef5b4eceb8d2</image:loc>
      <image:title>NVIDIA Launches Ising — World's First Open Quantum AI Models</image:title>
      <image:caption>NVIDIA released **Ising**, the world's first open-source AI model family for quantum computing, covering two hard problems: processor calibration (vision-language model) and error-correction decodi...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>NVIDIA Launches Ising — World's First Open Quantum AI Models</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/your-agent-needs-a-soul-you-can-t-write-from-scratch</loc>
    <lastmod>2026-05-18T21:03:17.239Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/6f0197bb-61aa-40dd-bd44-456155127855</image:loc>
      <image:title>"Your agent needs a SOUL you can't write from scratch"</image:title>
      <image:caption>The hardest problem in the agent space isn't infrastructure — it's that the people deploying agents can't describe their own work at the resolution an agent needs to act on it. The more senior and ...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-16</news:publication_date>
      <news:title>"Your agent needs a SOUL you can't write from scratch"</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-writes-code-you-own-quality</loc>
    <lastmod>2026-05-18T21:02:47.860Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/80d82061-0f9c-459c-b0db-a2f7d1317777</image:loc>
      <image:title>AI Writes Code. You Own Quality.</image:title>
      <image:caption>AI is a speed multiplier, not a quality guarantee — and multipliers amplify both strengths and weaknesses. The engineer's job shifts from *writing* code to *owning* it: defining tests first, enforc...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-15</news:publication_date>
      <news:title>AI Writes Code. You Own Quality.</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/i-tested-claude-code-against-3-open-source-alternatives-and-one-came-surprisingly-close</loc>
    <lastmod>2026-05-18T21:02:22.683Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b0e29d36-96d2-4bae-9130-f259bc443ae9</image:loc>
      <image:title>I tested Claude Code against 3 open-source alternatives, and one came surprisingly close</image:title>
      <image:caption>OpenCode, Cline, and Aider all replicate Claude Code's surface capabilities (multi-file reads, command execution, iteration) but differ fundamentally in architecture. OpenCode runs as a local **age...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-15</news:publication_date>
      <news:title>I tested Claude Code against 3 open-source alternatives, and one came surprisingly close</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/clawgui-a-unified-framework-for-training-evaluating-and-deploying-gui-agents</loc>
    <lastmod>2026-05-18T21:01:20.301Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/2b9ad388-11f8-4a27-9e2c-da390bfd3cab</image:loc>
      <image:title>ClawGUI — A Unified Framework for Training, Evaluating, and Deploying GUI Agents</image:title>
      <image:caption>ClawGUI is a full-stack open-source framework (GitHub:</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-15</news:publication_date>
      <news:title>ClawGUI — A Unified Framework for Training, Evaluating, and Deploying GUI Agents</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/beyond-prompt-engineering-why-openai-s-o1-is-the-new-logic-engine-for-ai-agents</loc>
    <lastmod>2026-06-04T03:45:09.256Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/6ad99ead-7b59-4812-8e1f-b56abe66aa80</image:loc>
      <image:title>Beyond Prompt Engineering: Why OpenAI’s o1 is the New Logic Engine for AI Agents</image:title>
      <image:caption>Beyond Prompt Engineering: Why OpenAI’s o1 is the New Logic Engine for AI Agents If you spend your day tweaking system prompts, adding "think step-by-step" instructions, or building complex few-shot examples to prevent hallucinations in...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-14</news:publication_date>
      <news:title>Beyond Prompt Engineering: Why OpenAI’s o1 is the New Logic Engine for AI Agents</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/llama-3-1-405b-the-open-weights-era-just-got-real</loc>
    <lastmod>2026-06-04T03:44:53.468Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/e707320b-f075-4e18-b620-80c6932f8c86</image:loc>
      <image:title>Llama 3.1 405B: The Open-Weights Era Just Got Real</image:title>
      <image:caption>Llama 3.1 405B: The Open-Weights Era Just Got Real If you have been building your entire AI stack around OpenAI or Anthropic APIs, the landscape just shifted under your feet.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-13</news:publication_date>
      <news:title>Llama 3.1 405B: The Open-Weights Era Just Got Real</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/openclaw-a-secure-local-first-agent-runtime</loc>
    <lastmod>2026-05-18T20:59:33.293Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/1ec77517-69ee-46cf-8503-6eebd7fcf101</image:loc>
      <image:title>OpenClaw — a secure local-first agent runtime</image:title>
      <image:caption>Key Takeaways: OpenClaw Gateway & Secure Agent Execution What OpenClaw Is - A local agent runtime with a gateway control plane - Orchestrates model reasoning → skill selection → controlled tool execution - Designed for secure, local-first...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-12</news:publication_date>
      <news:title>OpenClaw — a secure local-first agent runtime</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-end-of-the-closed-source-moat-why-llama-3-1-405b-changes-the-developer-math</loc>
    <lastmod>2026-06-04T03:43:37.783Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/5283a74a-64ef-45a2-8845-825053eca77e</image:loc>
      <image:title>The End of the Closed-Source Moat: Why Llama 3.1 405B Changes the Developer Math</image:title>
      <image:caption>The End of the Closed-Source Moat: Why Llama 3.1 405B Changes the Developer Math If you have been building LLM-powered applications over the last year, you have likely been trapped in a fundamental trade-off: use the "frontier" models...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-12</news:publication_date>
      <news:title>The End of the Closed-Source Moat: Why Llama 3.1 405B Changes the Developer Math</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/skillclaw-let-skills-evolve-collectively-with-agentic-evolver</loc>
    <lastmod>2026-05-18T20:58:41.896Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/9fee235a-660d-48be-8ec1-60f93c7115cb</image:loc>
      <image:title>SkillClaw: Let Skills Evolve Collectively with Agentic Evolver</image:title>
      <image:caption>Source: huggingface.co</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-11</news:publication_date>
      <news:title>SkillClaw: Let Skills Evolve Collectively with Agentic Evolver</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/these-8-steps-are-what-missing-from-your-workflow</loc>
    <lastmod>2026-06-11T15:41:30.911Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/4052a1c4-3fbb-4335-a47f-a85bdf9415a7</image:loc>
      <image:title>These 8 Steps Are What Missing From Your Workflow</image:title>
      <image:caption>60 years of software engineering still applies — now it's scaffolding for agents. The video covers 7 things to set up *before* writing a prompt: PRD via planner agent, tailored `CLAUDE.md`, agents/...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-11</news:publication_date>
      <news:title>These 8 Steps Are What Missing From Your Workflow</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/gpt-4o-s-end-to-end-multimodality-the-death-of-the-cascaded-pipeline</loc>
    <lastmod>2026-06-04T03:42:29.937Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/3816b009-5ee7-463f-a773-1c1cbbfc60a3</image:loc>
      <image:title>GPT-4o’s End-to-End Multimodality: The Death of the Cascaded Pipeline</image:title>
      <image:caption>GPT-4o’s End-to-End Multimodality: The Death of the Cascaded Pipeline The release of GPT-4o on May 13, 2024, is often framed by mainstream media as a victory for "human-like" interaction and lower latency.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-11</news:publication_date>
      <news:title>GPT-4o’s End-to-End Multimodality: The Death of the Cascaded Pipeline</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/neuro-symbolic-ai-just-made-training-100x-cheaper-here-s-why-you-should-care</loc>
    <lastmod>2026-06-04T03:42:12.385Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/4232c79a-8cde-4442-9e2c-07e10b1b79c9</image:loc>
      <image:title>Neuro-Symbolic AI Just Made Training 100x Cheaper—Here's Why You Should Care</image:title>
      <image:caption>Neuro-Symbolic AI Just Made Training 100x Cheaper—Here's Why You Should Care OpenAI dropped GPT-5.4. Anthropic is shipping agent teams. Google refreshed Gemini.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-09</news:publication_date>
      <news:title>Neuro-Symbolic AI Just Made Training 100x Cheaper—Here's Why You Should Care</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/anthropic-cuts-third-party-harnesses-from-claude-subscriptions</loc>
    <lastmod>2026-06-04T03:44:17.003Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/894ffcca-9f71-4ce1-b522-466763f9aef2</image:loc>
      <image:title>Anthropic Cuts Third-Party Harnesses from Claude Subscriptions</image:title>
      <image:caption>Anthropic blocks third-party harnesses like OpenClaw from Claude Pro and Max subscriptions, forcing developers onto pay-as-you-go billing. The move affects thousands of developers who relied on subscription-based access through external tools.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-08</news:publication_date>
      <news:title>Anthropic Cuts Third-Party Harnesses from Claude Subscriptions</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-code-source-leak-npm</loc>
    <lastmod>2026-05-18T20:56:31.523Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/966b4926-81e9-46b5-bf0e-62cdbd148947</image:loc>
      <image:title>Claude Code Source Leaked via npm Source Map</image:title>
      <image:caption>Claude Code Source Leaked via npm Source Map Anthropic's Claude Code CLI tool had its full TypeScript source code accidentally exposed through source map files included in an npm package release, revealing the internal architecture of one...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-07</news:publication_date>
      <news:title>Claude Code Source Leaked via npm Source Map</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/claude-code-rebuild-100k-stars</loc>
    <lastmod>2026-05-18T20:56:05.653Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/6d4b4764-8a8b-4594-9966-5cadb9ee3800</image:loc>
      <image:title>One Developer Rebuilt Claude Code Overnight and Got 100K Stars</image:title>
      <image:caption>One Developer Rebuilt Claude Code Overnight and Got 100K Stars After Anthropic's Claude Code source was accidentally exposed via npm source maps in late March 2026, developer Simon Willison and others began studying the leaked architecture.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-07</news:publication_date>
      <news:title>One Developer Rebuilt Claude Code Overnight and Got 100K Stars</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/free-claude-code-credits-claim-up-to-200-before-april-17</loc>
    <lastmod>2026-05-18T21:15:59.769Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/d40a349b-3c84-4088-83ff-1e9f36d95197</image:loc>
      <image:title>Free Claude Code Credits: Claim Up to $200 Before April 17</image:title>
      <image:caption>Anthropic is giving away free Extra Usage credits to Claude Pro and Max subscribers -- but you need to act before April 17, 2026.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-07</news:publication_date>
      <news:title>Free Claude Code Credits: Claim Up to $200 Before April 17</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/why-google-s-new-code-llm-update-will-change-how-developers-write-ai-powered-tools-and-why-you-should-care</loc>
    <lastmod>2026-05-18T20:55:11.128Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/11acae91-7847-420a-9e96-c81c8c24fa19</image:loc>
      <image:title>Why Google's New Code LLM Update Will Change How Developers Write AI-Powered Tools — and Why You Should Care</image:title>
      <image:caption>Title: Why Google's New Code LLM Update Will Change How Developers Write AI-Powered Tools — and Why You Should Care By VybeCoding.ai --- In a quiet but impactful update released on April 5, 2024, Google introduced a new version of its...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-04-03</news:publication_date>
      <news:title>Why Google's New Code LLM Update Will Change How Developers Write AI-Powered Tools — and Why You Should Care</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/nvidia-nemotron-3-super-the-open-weight-coding-model-you-should-be-building-on</loc>
    <lastmod>2026-06-04T03:40:53.188Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/af4270ad-f9aa-4d2e-a155-3af74939b011</image:loc>
      <image:title>NVIDIA Nemotron 3 Super: The Open-Weight Coding Model You Should Be Building On</image:title>
      <image:caption>NVIDIA's Nemotron 3 Super Is the Open-Weight Coding Model You Should Be Building On NVIDIA dropped Nemotron 3 Super at GTC 2026. The benchmark that matters crossed 60%. Here's what that unlocks.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-03-28</news:publication_date>
      <news:title>NVIDIA Nemotron 3 Super: The Open-Weight Coding Model You Should Be Building On</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/xiaomi-s-free-mimo-v2-pro-lands-this-week-and-it-nearly-matches-claude-opus-4-6</loc>
    <lastmod>2026-06-04T03:40:25.436Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/5e1a9bb0-fb92-4360-ac6b-6e14750d3d44</image:loc>
      <image:title>Xiaomi's Free MiMo-V2-Pro Lands This Week — and It Nearly Matches Claude Opus 4.6</image:title>
      <image:caption>Now I have strong facts to write the article. Let me write it about Xiaomi's MiMo-V2-Pro, released March 18, 2026 — the most concrete, developer-relevant story from this week.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-03-28</news:publication_date>
      <news:title>Xiaomi's Free MiMo-V2-Pro Lands This Week — and It Nearly Matches Claude Opus 4.6</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/mcp-just-hit-97-million-installs-the-protocol-wars-are-over</loc>
    <lastmod>2026-06-05T16:41:51.627Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/d0c8620c-0892-4e58-b2af-407b3ae24990</image:loc>
      <image:title>MCP Just Hit 97 Million Installs. The Protocol Wars Are Over.</image:title>
      <image:caption>If you're building with AI and you haven't adopted Model Context Protocol yet, March 2026 is the month you ran out of excuses. MCP crossed 97 million installs on March 25th — and with over 4,000 published servers now covering everything...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-03-26</news:publication_date>
      <news:title>MCP Just Hit 97 Million Installs. The Protocol Wars Are Over.</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/nvidia-s-agent-toolkit-makes-autonomous-ai-agents-safe-enough-to-actually-ship</loc>
    <lastmod>2026-06-04T03:39:18.563Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ddb504e7-7cb7-492b-af37-214aa5054349</image:loc>
      <image:title>NVIDIA's Agent Toolkit Makes Autonomous AI Agents Safe Enough to Actually Ship</image:title>
      <image:caption>NVIDIA's Agent Toolkit Makes Autonomous AI Agents Safe Enough to Actually Ship Building autonomous AI agents has never been the hard part — keeping them from doing something catastrophically wrong has.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-03-23</news:publication_date>
      <news:title>NVIDIA's Agent Toolkit Makes Autonomous AI Agents Safe Enough to Actually Ship</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-ai-developer-landscape-just-shifted-what-march-2026-s-model-wave-means-for-your-stack</loc>
    <lastmod>2026-06-04T03:38:59.093Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/f5eec120-f3cc-4880-a5ff-439a8429b00a</image:loc>
      <image:title>The AI Developer Landscape Just Shifted: What March 2026's Model Wave Means for Your Stack</image:title>
      <image:caption>The AI Developer Landscape Just Shifted: What March 2026's Model Wave Means for Your Stack The first three weeks of March 2026 delivered more AI capability per calendar day than most of 2024 combined.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-03-22</news:publication_date>
      <news:title>The AI Developer Landscape Just Shifted: What March 2026's Model Wave Means for Your Stack</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-antigravity-enters-the-ai-ide-wars-the-battle-for-developer-mindshare-heats-up</loc>
    <lastmod>2026-06-04T03:38:43.928Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/936d87e1-8b4d-4673-a145-29de7df93976</image:loc>
      <image:title>Google Antigravity Enters the AI IDE Wars: The Battle for Developer Mindshare Heats Up</image:title>
      <image:caption>Google Antigravity Enters the AI IDE Wars: The Battle for Developer Mindshare Heats Up Breaking: Google launches Antigravity, an agentic development platform powered by Gemini 3, joining an increasingly crowded field of AI-powered IDEs...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-02-05</news:publication_date>
      <news:title>Google Antigravity Enters the AI IDE Wars: The Battle for Developer Mindshare Heats Up</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-great-ai-coding-shift-43-million-pull-requests-per-month-are-human-developers-becoming-obsolete</loc>
    <lastmod>2026-06-05T16:40:49.344Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/64c92447-8142-4638-9531-426980994f9f</image:loc>
      <image:title>The Great AI Coding Shift: 43 Million Pull Requests Per Month - Are Human Developers Becoming Obsolete?</image:title>
      <image:caption>GitHub reports 43 million pull requests monthly - a 23% surge driven by AI coding tools. But as Cursor eats Copilot's lunch and initial enthusiasm wanes, are developers facing replacement or evolution? The uncomfortable truth about AI coding in 2026.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2026-01-12</news:publication_date>
      <news:title>The Great AI Coding Shift: 43 Million Pull Requests Per Month - Are Human Developers Becoming Obsolete?</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/google-s-gemini-2-5-deep-think-achieves-gold-medal-at-icpc-world-finals</loc>
    <lastmod>2026-06-04T03:38:26.575Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/cc7b4bbd-f57f-46b5-ad3d-de54d5b7132c</image:loc>
      <image:title>Google's Gemini 2.5 Deep Think Achieves Gold Medal at ICPC World Finals</image:title>
      <image:caption>Google's Gemini 2.5 Deep Think Achieves Gold Medal at ICPC World Finals: A Historic AI Milestone In a groundbreaking achievement announced on October 9, 2025, Google's Gemini 2.5 Deep Think model reached gold-medal level performance at the...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2025-10-11</news:publication_date>
      <news:title>Google's Gemini 2.5 Deep Think Achieves Gold Medal at ICPC World Finals</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-agents-lead-the-charge-october-2025-s-top-ai-developments</loc>
    <lastmod>2026-06-05T16:44:06.491Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b36e950f-3d6b-409b-b4c6-8fc210d702bc</image:loc>
      <image:title>AI Agents Lead the Charge: October 2025's Top AI Developments</image:title>
      <image:caption>AI agents emerge as the fastest-advancing technology in October 2025, with major developments in e-commerce, healthcare, and manufacturing reshaping industries.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2025-10-11</news:publication_date>
      <news:title>AI Agents Lead the Charge: October 2025's Top AI Developments</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/microsoft-launches-agent-framework-democratizing-ai-agent-development</loc>
    <lastmod>2026-06-04T03:38:13.330Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/b81f0ee4-ad89-453f-94f0-e1fe5adf59d9</image:loc>
      <image:title>Microsoft Launches Agent Framework: Democratizing AI Agent Development</image:title>
      <image:caption>Microsoft Launches Agent Framework: Democratizing AI Agent Development Category: AI Development Tags: Microsoft, Agent Framework, .NET, Python, Open Source, AI Agents Date: October 11, 2025 Microsoft announced a preview of its Agent...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2025-10-11</news:publication_date>
      <news:title>Microsoft Launches Agent Framework: Democratizing AI Agent Development</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/the-top-ai-coding-tools-dominating-2025-what-developers-are-really-using</loc>
    <lastmod>2026-06-11T15:40:33.430Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/17da6912-a5de-4857-90e9-50f0c98ec41b</image:loc>
      <image:title>The Top AI Coding Tools Dominating 2025: What Developers Are Really Using</image:title>
      <image:caption>The Top AI Coding Tools Dominating 2025: What Developers Are Really Using Category: Developer Tools Tags: AI Coding, Cursor, Claude Code, Windsurf, GitHub Copilot, Developer Survey Date: October 11, 2025 As we move through 2025, the...</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2025-10-11</news:publication_date>
      <news:title>The Top AI Coding Tools Dominating 2025: What Developers Are Really Using</news:title>
    </news:news>
  </url>
  <url>
    <loc>https://vybecoding.ai/news/ai-coding-revolution-september-2025-state-of-the-market</loc>
    <lastmod>2026-06-04T03:35:25.568Z</lastmod>
    <changefreq>daily</changefreq>
    <priority>0.6</priority>
    <image:image>
      <image:loc>https://modest-lobster-37.convex.cloud/api/storage/ae09fe14-72a3-450e-8598-12f35b9c8668</image:loc>
      <image:title>AI Coding Revolution: September 2025 State of the Market</image:title>
      <image:caption>September 2025: Claude Code leads with multi-agent orchestration, Cursor dominates enterprise adoption, while Augment Code and Codeium emerge as strong challengers. The AI coding tool market evolves beyond simple completion to autonomous development partners.</image:caption>
    </image:image>
    <news:news>
      <news:publication>
        <news:name>vybecoding.ai</news:name>
        <news:language>en</news:language>
      </news:publication>
      <news:publication_date>2025-09-16</news:publication_date>
      <news:title>AI Coding Revolution: September 2025 State of the Market</news:title>
    </news:news>
  </url>
</urlset>