AcademyMCP serversDevelopment

MartinLoop

Engineering teams that hand real coding jobs to an agent and want limits and a clear record of each run.

  • Recommendedour rating
  • 409gitHub stars
  • Apache-2.0licence
  • 2 days agolast update
claude mcp add martin-loop -- npx -y @martinloop/mcp
README.md

Loading the file...

What it does

MartinLoop is a governed runtime for AI coding agents. The agent still writes the code, while MartinLoop applies budget caps, stop conditions and verifier gates, and keeps rollback evidence. Each run ends with an inspectable receipt of what happened.

Use cases

  1. 01Set a budget cap on an agent coding job
  2. 02Verify agent output before accepting it
  3. 03Review a receipt of what a run changed

Questions about
MartinLoop.

What is MartinLoop used for?

Engineering teams that hand real coding jobs to an agent and want limits and a clear record of each run. MartinLoop is a governed runtime for AI coding agents. The agent still writes the code, while MartinLoop applies budget caps, stop conditions and verifier gates, and keeps rollback evidence. Each run ends with an inspectable receipt of what happened.

How do I install MartinLoop?

Run this in your terminal: claude mcp add martin-loop -- npx -y @martinloop/mcp

Is MartinLoop open source?

Yes. The code is on GitHub (Keesan12/martin-loop) under the Apache-2.0 licence.

Is MartinLoop safe to use?

It passed our automatic scan for credential theft, hidden instructions and risky install commands. Third party open source software. Sabemos AI does not maintain it. Check the code and permissions before you connect it to company data.