Launching today

AgentLoop

Launching today

Starts a fresh Codex worker and critic every cycle

20 followers

Starts a fresh Codex worker and critic every cycle

20 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.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

Framer AI AgentsDesign and publish professional sites with AI

Promoted

OpenAI

OpenAI Day

How did GPT-5.6 change the ambition or scope of what you shipped?

AgentLoop

Maker

GPT-5.6 changed AgentLoop from a small automation script into a complete local developer tool. I designed the architecture and product decisions, then used Codex CLI with GPT-5.6 to implement and review the daemon, filesystem state, fresh-context worker and critic cycles, MCP bridge, sandbox boundaries, cancellation, and live dashboard in focused sessions. Its ability to navigate a real codebase, run tests, inspect failures, and implement complete product slices let me attempt a much broader project as a solo developer. GPT-5.6 did not just help build AgentLoop. Through Codex, it now powers both the fresh worker and independent critic in every cycle.

Report

2h ago

AgentLoop

Maker

📌

Hey Product Hunt, I’m Edward, the solo developer behind AgentLoop. I built it because I kept becoming the relay between ChatGPT and Codex: plan, paste, inspect, return feedback, repeat. Quality slipped as soon as I stopped watching. AgentLoop automates that relay without hiding the work. Set a goal and GUIDELINES.md rubric once. Each cycle starts a fresh Codex worker, then a fresh critic tests the result against your rubric and writes concrete fix notes for the next worker. Project files carry memory between clean contexts, and a local dashboard makes every cycle watchable and cancellable. The moment the idea proved itself was an evaluation with no forced failure. The first worker produced nine passing tests, but the fresh critic still found a real mixed percent-decoding defect. The next worker fixed it, added regression coverage, passed 11 tests, and earned PASS. I designed and built AgentLoop during OpenAI Build Week using Codex CLI and GPT-5.6. It is open source and zero-dependency Node.js. What coding task would you trust an observable loop to handle while you step away?

Report

20h ago

Fresh worker and critic each cycle is the right instinct, and the file-as-memory part is where I'd expect trouble. We ran a loop like this and hit critic flip-flop: the same code passed one cycle and failed the next, because nothing in the carried notes told the new critic what had already been tried and accepted. We ended up requiring two consecutive passes before calling it done. Do the fix notes accumulate across cycles, and does polish mode have a hard cycle cap?

Report

2h ago