Keesan12 / martin-loop
Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agents swarms overnight and get your time back.
Why this job: says: coding agents; topics: coding-agents, claude-code, codex
What it does
- Budget caps stop the next attempt before a configured USD, token, or iteration limit is exceeded.
- Verifier gates require a real check, such as npm test, before a run can count as complete.
- Policy checks block unsafe verifier commands, risky path changes, and secret-like task inputs before execution.
- Failure classification uses canonical runtime classes for triage and reporting. See Failure Taxonomy (13 Runtime Classes).
- Run receipts capture stop reason, verifier evidence, budget posture, integrity state, and the next safe action.
Get started
npx -y martin-loop@latest enable --engine codex- Maintenance
- Active
- Last commit 6 days ago
- Stars
- 286
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.9.0
- Released 6 days ago
- Built with
- TypeScript
- 88% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 92% closed
- 1 still open
- Pull requests
- 234 merged
- 0 waiting
- Releases
- 119
- 30+ in the last year
More: languages, topics and project record
Languages
- TypeScript 88%
- JavaScript 12%
- PowerShell <1%
- Shell <1%
Topics
- agent-runtime
- ai-agent-runtime
- ai-coding-agents
- ai-control-plane
- ai-governance
- ai-safety
- audit-trail
- budget-enforcement
- claude-code
- codex
- coding-agents
- control-plane
Project record
- JobCoding agents
- StatusListed
- Commits1,061
- Forks30
- Watching1
- Stars in 28 days-4
- CreatedApr 4, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026