Introducing Expect
Let agents test your code in a real browser
1. Run Claude Code / Codex to QA your app
2. Watch a video of every bug found
3. Fix and repeat until passing
Run as a CLI or agent skill. Fully open source
Claude 4 just refactored my entire codebase in one call.
25 tool invocations. 3,000+ new lines. 12 brand new files.
It modularized everything. Broke up monoliths. Cleaned up spaghetti.
None of it worked.
But boy was it beautiful.
๐ฅ Thatโs the sauce.
Retweet to flex on your dev circle.
Bookmark to never touch StackOverflow again.
Follow for more tech you wonโt find on HackerNews. ๐
#AI#DevTools#BuildInPublic#IndieHacking
๐จ Thread: 7 Underground AI Tools Thatโll Make You Look Like a 10x Dev ๐๐ป
These arenโt the usual ChatGPT / Copilot types.
These are off-the-grid, niche, crazy powerful AI tools that devs need to start flexing in 2025.
๐งต๐
7. ๐ค AgentOps
AI agents that can test, debug, improve, and monitor themselves.
Yes โ self-healing AI agents.
Plug it into your AI workflows and chill.
Literally feels illegal to use ๐ณ