Skip to content

Keesan12/Martin-Loop

AI Agents & Assistants

A tool that gives AI coding agents budgets, stop conditions, rollback rules, and audit receipts to keep executions bounded and inspectable

TypeScript Latest v0.4.5 · 7d ago Security brief →

Features

  • Enforces explicit contracts (budgets, verifiers, stop conditions) for AI coding runs
  • Generates detailed run receipts with spend, verifier results, and rollback evidence
  • Provides interactive "Arcade" mode to keep terminals useful during long governed executions

Recent releases

View all 53 releases →
No immediate action
v0.4.5 New feature

MartinLoop Arcade

No immediate action
v0.4.3 Bug fix

Budget consistency + command context

No immediate action
v0.4.2 Bug fix

Error normalization + Codex diagnostics

Review required
v0.4.1 Breaking risk
Auth Dependencies

Receipt defaults + preflight fix

No immediate action
v0.4.0 Bug fix

Version alignment fix

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

About

Stars
38
Forks
3
Languages
TypeScript JavaScript
Downloads/week
45 ↑14%
NPM Maintainers
1 Single npm maintainer
Contributors
4

Install & Platforms

Install via
npm

Beta — feedback welcome: [email protected]