Found MartinLoop through a thread on Hacker News where someone was venting about a Claude Code run that estimated $2.40 and ended up burning $65 in retries before they noticed. Felt that pain personally so I clicked through and gave it a try. Spent the last 2 weeks running it as a wrapper around my Codex and Claude Code workflows for a side project. The whole "give the agent a finish line" concept clicks immediately when you've ever watched an agent loop on itself overnight.
The killer features for me are the hard budget caps and the verifier gates. You set a dollar limit before the run, point it at your test suite (like npm test), and the agent stops when it hits either the budget or a clean verifier pass. No more "wake up to a $300 OpenAI bill because the agent kept retrying a typo." The JSONL run records are also surprisingly useful when something does go sideways. You get a clean receipt of what changed, what passed, what failed, and exactly where the spend went.
Where it gets rough: setup is CLI-only right now, no hosted dashboard yet (it's on the waitlist for Pro tier). Side effects that escape the repo boundary, like DB migrations or external API calls, still need manual fencing through safety policy. Not a deal breaker but you do need to think about scope upfront. Apache 2.0 license and npm install -g martin-loop to get started means there's zero friction to try it. For anyone running coding agents in production or even just for side projects, this fixes a real problem that nobody else is addressing seriously
thanks Nolan, yes we're shipping at a fast clip right now over 40+ releases in less than 60 days, and we do have the dashboard and some great new features coming that other teams have asked for, look out for it soon or sign up on the website for updates when it launches. martinloop.com