AgentLoop

Starts a fresh Codex worker and critic every cycle

92 followers

Starts a fresh Codex worker and critic every cycle

92 followers

Visit website

AI Coding Agents

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.

AgentLoop Alternatives

Exploring alternatives to AgentLoop? Try Cursor for in-editor AI pair programming, Claude Code for deep-context refactors, Codex 3.0 by OpenAI for auto build/test/debug, Windsurf for an agentic IDE, and Augment Code for production-grade fixes. Compare autonomy, iteration speed, and critique quality to fit your workflow.