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.
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?
The fresh worker + critic loop is the part I'd want to test first. Long agent chats usually get weird after a few context turns; using project files as memory feels cleaner, but I'm curious how you keep the critic from becoming the bottleneck on larger repos.
fresh worker and fresh critic every cycle is a smart way to dodge the context-rot problem long-running agent chats get into, where it starts agreeing with its own earlier mistakes. the part I'm curious about is the rubric itself, GUIDELINES.md is only as good as what you thought to write into it upfront. if the critic passes something that's technically rubric-compliant but wrong in a way you didn't anticipate when you wrote the rubric, is there a way to catch that besides just noticing later and rewriting the file
The project-files-as-memory idea is the interesting part for me. I’ve hit the opposite failure: too much chat context making the agent less reliable. Which type of work has shown the biggest quality jump so far bug fixes or multi-file features?
the flip-flop question covers consistency across cycles, but what about a single critic being wrong in the moment - it fails code that was actually correct, and the next worker "fixes" it by changing something that didn't need changing, possibly introducing a real bug while chasing a phantom one. since the worker just trusts the fix note as ground truth with no way to push back, is there any check for the worker disagreeing with a critic's fail, or is a bad critic call just as final as a good one
Congrats on the launch! If you cancel a cycle mid-run from the dashboard, does it roll back the worker's in-progress changes, or do partial edits stay on disk until the next cycle sorts them out?
Nice one, congrats on the launch. The relay between ChatGPT and Codex is painfully familiar. You start out supervising the work, then somehow end up doing project management for two AI tools. The fresh critic idea is the part that stands out for me. I’d be interested to see how it behaves on a larger codebase where the tests are incomplete or the problem is architectural rather than a clean bug fix. Also, can you cap how much of the codebase it is allowed to touch in each loop? That would probably be the difference between me trusting it and hovering over the dashboard anyway.
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?
About AgentLoop on Product Hunt
“Starts a fresh Codex worker and critic every cycle”
AgentLoop launched on Product Hunt on July 23rd, 2026 and earned 105 upvotes and 17 comments, placing #19 on the daily leaderboard. 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 was featured in Open Source (68.6k followers), Developer Tools (516.3k followers), Artificial Intelligence (474.4k followers), GitHub (41.3k followers) and OpenAI Day (9 followers) on Product Hunt. Together, these topics include over 225.8k products, making this a competitive space to launch in.
Who hunted AgentLoop?
AgentLoop was hunted by Edward Yi. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how AgentLoop stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Edward Yi