AgentLoop - Starts a fresh Codex worker and critic every cycle
AgentLoop
Starts a fresh Codex worker and critic every cycle
Screenshots
Hunter's comment
Unlike long-running agent chats, AgentLoop starts a fresh Codex worker and critic every cycle. Set the goal and GUIDELINES.md rubric once; workers build, critics test, and failures become concrete fix notes for the next clean context. Project files carry the memory. Runs stay local, sandboxed, observable, and cancellable from a live dashboard, with ChatGPT control through MCP. Polish mode can continue beyond PASS until the critic says SHIP. Open source and zero-dependency Node.js.
Link
This is posted on Steemhunt - A place where you can dig products and earn STEEM.
View on Steemhunt.com
Thank you for sharing on steem! I'm witness fuli, and I've given you a free upvote. If you'd like to support me, please consider voting at https://steemitwallet.com/~witnesses 🌟
Congratulations!
We have upvoted your post for your contribution within our community.
Thanks again and look forward to seeing your next hunt!
Want to chat? Join us on: