martin-loop
Active·★ 26·Apache-2.0·Updated 2026-05-27
★ Trending★ Security & Safety
The control plane for autonomous work and coding agent teams.
MartinLoop is a governance layer for AI coding loops that enforces budget caps, verifier gates, rollback evidence, and audit trails. It prevents unbounded retries by stopping unsafe or uneconomical work before execution, providing visibility and accountability for autonomous coding agents.
#agent-runtime#ai-agent-runtime#ai-coding-agents#ai-control-plane#ai-governance#ai-safety#audit-trail#budget-enforcement
01
Features
01Budget governance with hard caps on USD, iterations, and tokens
02Verifier gate that blocks execution unless verification passes
03Failure taxonomy classifying 11 failure classes
04Safety leash evaluating commands, file scope, and secrets before execution
05Rollback evidence capturing state before and after each attempt
02
Compatibility
Node.js
Node >=20
Verified via docs
TypeScript
TypeScript strict
Verified via docs
npm
npm package
Verified via docs
03
Quick start
1
$ npm install -g martin-loop
04
Use cases
↳Bounding AI agent retry loops with budget and safety constraints
↳Auditing AI coding runs with structured JSONL records
↳Enforcing policy-as-code for autonomous coding agents
05
Alternatives
awesome-n8n-templates★ 22.6k
Supercharge your workflow automation with this curated collection of n8n templates! Instantly connect your favorite apps-like Gmail, Telegram, Google Drive, Slack, and more-with ready-to-use, AI-powered automations. Save time, boost productivity, and unlock the true potential of n8n in just a few clicks.
FastMCP★ 25.4k
The fast, Pythonic way to build MCP servers and clients. Designed by the Pydantic team for type safety and speed.
agentic-ai★ 140
This repository serves as a comprehensive knowledge hub, curating cutting-edge research papers and developments across 24 specialized domains
golemcore-bot★ 40
AI-native runtime for the GolemCore ecosystem with skills, plugins, MCP, memory, and Hive.
Related searches
Comments
Log in to leave a comment
- Parker RiveraApr 26, 2026
Handles agent-to-agent communication and work routing cleanly.
- Elliot RiveraApr 16, 2026
Control plane for autonomous agent teams is exactly the infrastructure layer that's been missing.
- AAspen PatelMar 18, 2026
The "autonomous work" framing is accurate — agents coordinate without constant human direction.
- Oakley LeeMar 1, 2026
Good for coordinating coding agent teams where task distribution matters.