MARTINLOOP

MartinLoop — Safe AI coding agents for real software work.

AI agents can write code now. The hard part is trusting them with real software work. MartinLoop wraps every AI coding run with a budget, stop rule, verifier, rollback, and receipt — so teams can use Claude, Codex, Cursor, and other agents without runaway cost or invisible risk. Not another coding agent. The safety system around the agents you already use.

Open source · Apache 2.0 licensed · martin-loop on npm · Keesan12/martin-loop on GitHub

npm install -g martin-loop
martin run "your task" --budget 3 --verify "pnpm test"
martin inspect

AI agents can write code now. The hard part is trusting them with real software work.

Agents read repos, edit files, run commands, retry tasks, and produce changes teams may merge. The new question is not whether AI can write code — it is whether you can trust the work it just did. MartinLoop gives every agent run a budget, stop rule, verifier, rollback path, and receipt before the change lands.

Not another coding agent.

Claude writes. Codex works through the task. Cursor helps developers move faster. MartinLoop is the safety system around the agents you already use — budgets, stop rules, verification, rollback, and receipts. The agents stay. The risk goes away.

Five things happen on every MartinLoop run.

  1. Smarter retries. Failed attempts compressed into structured signals — not dumped back raw. Token usage stays flat.
  2. Targeted failure handling. 12 failure classes, each with a different fix. Syntax errors get constraint repairs. Hallucinations get grounding checks.
  3. Hard budget cap. Set a dollar limit before the run starts. MartinLoop tracks spend in real time and stops before the cap.
  4. Smart exits. MartinLoop exits with a clean result when diminishing returns kick in or the budget ceiling approaches.
  5. Accurate cost accounting. Every token counted — including thinking tokens and sub-agent spend. No more under-reporting.

Pricing

  • Open Source Core — Free. Full safety layer. Apache 2.0 licensed. CLI, local budget caps, stop rules, --verify gate, rollback evidence, and JSONL run receipts.
  • Developer Pro, Team, Growth, Business, Enterprise — Coming soon. Paid plans with hosted dashboard, team controls, and enterprise governance are in early access. Join the waitlist.

FAQ

What is MartinLoop?
The trust and safety layer around AI coding agents. Every run gets a budget, stop rule, verifier, rollback path, and receipt — without changing which agent or model you use.
Is this another coding agent?
No. Claude, Codex, and Cursor are the workers. MartinLoop is the safety system around the work they do.
Is MartinLoop open source?
Yes. The core is Apache 2.0 licensed. The hosted dashboard and managed team safety layer are commercial.
Who is it for?
Engineering teams, platform teams, and CTOs running AI coding agents in production who need control, auditability, and a record of what happened.