peg/rampart

Open-source firewall for AI agents. Policy engine that controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.

44
/ 100
Emerging

This tool helps developers safely use AI coding assistants by acting as a firewall for their commands. It takes your AI agent's proposed actions (like running code or accessing files) and checks them against your security rules. The output is either the allowed action proceeding or a blocked action with a clear reason, ensuring your AI assistant doesn't accidentally damage your system or leak sensitive data. Developers, especially those experimenting with autonomous AI agents, are the primary users.

Use this if you want to set clear boundaries and ensure your AI coding assistant, such as Claude Code, OpenClaw, or others, operates only within defined, safe parameters on your machine.

Not ideal if you are not using AI coding assistants or if you require a system-wide security solution beyond protecting specific AI agent interactions.

AI-safety developer-tools secure-coding agent-governance software-development
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 15 / 25

How are scores calculated?

Stars

49

Forks

8

Language

Go

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/peg/rampart"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.