Introducing agent-browser chat agent-browser is now a browser agent. → One-shot: agent-browser chat "open google, search for dogs" → Interactive: agent-browser chat → Built-in AI chat in the dashboard → Execute any agent-browser command → Use agent-browser as a sub-agent

agent-browser now has 1,000,000 weekly downloads
 One interesting datapoint: The dip lines up with switching npx → npm i -g The global install path gives us ~1ms startup What would you'd like to see next? How can we improve?

Embed Claude Code, Codex, Pi in your product with a few lines of code

agent-browser v0.27.2 is out Silent failures are now loud ones: → off-screen clicks scroll into view → dialogs no longer hang clicks → select errors list valid options → blocked clicks name what's covering them Plus ~150ms faster more npm i -g agent-browser

Fable 5 for code GPT-5.5 for review

emulate by @ctatedev is incredibly underrated, great work

ngrok has landed in Portless Keep your stable .localhost URLs while tunneling publicly For webhook testing, demos and sharing anything on the internet

zerolang is the most exciting thing I've ever built I've been programming for nearly 30 years. Since the day I learned to code, I've been obsessed. Late nights, weekends, vacations. Software has been the thing I've thought about more than almost anything else But this feels different I find myself thinking about zerolang constantly. Not just how to improve the language, but what it could mean for the future of software development In many ways, zerolang started with a question: "What if json-render was a programming language?" json-render was built around a simple idea: AI systems become dramatically more reliable when they operate on structured representations instead of unconstrained text and code Instead of generating arbitrary React, models generate validated UI specs Instead of guessing, they work within a defined semantic space zerolang takes that same idea and applies it to software itself What if programming languages were designed not only for humans, but also for agents? What if agents worked with semantic program graphs instead of source text? What if compilers exposed structure, changes, diagnostics directly instead of forcing models to reverse engineer them from strings? I believe that's where software development is heading We've made incredible progress in models, agent harnesses and dev tools It won't happen overnight. But I believe the way we build software will fundamentally change

This is surprisingly simple And it works

agent-browser by @ctatedev is absolutely crazy. every time I'm working on a frontend task, I let my agent grab screenshots to verify their work in the chat. absolute time saver.

portless is probably the biggest quality of life upgrade in my dev workflow this year. thank you @ctatedev! i add it to every project during the first few steps of scaffolding. running 10-20 dev servers simultaneously and having agents confirm their changes in browser feels overpowered.

Sign in with Vercel now supports wildcard .localhost callbacks Worktree-based local HTTPS origins like https://my-worktree.my-app.localhost are part of the normal dev workflow now This should become the industry standard Great ship by @vvoyer

Want: 𝚗𝚘𝚍𝚎 𝚏𝚖𝚝

Great advice Bonus: global agent-browser starts ~150x faster than npx bc it runs the Rust binary directly