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.
Intercepts system calls between AI agents and the OS using pattern matching (handling 95%+ of decisions in microseconds) with optional LLM-based verification for ambiguous cases. Integrates natively with Claude Code, OpenClaw, Cline, and Codex via hooks, shebangs, and LD_PRELOAD, while maintaining cryptographically hash-chained audit trails and real-time policy enforcement dashboards. Supports YAML-based policy rules with glob matching and hot-reload, MCP server proxying, and webhook-triggered approvals.
Stars
49
Forks
8
Language
Go
License
Apache-2.0
Category
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.
Featured in
Higher-rated alternatives
23blocks-OS/ai-maestro
AI Agent Orchestrator with Skills System - Give AI Agents superpowers: memory search, code graph...
ImKKingshuk/LockKnife
LockKnife: The Ultimate Android Security Research Tool. A unified TUI workspace and headless CLI...
FlineDev/ContextKit
Claude Code context engineering & planning system for individual AI development workflows
conorluddy/ios-simulator-skill
An IOS Simulator Skill for ClaudeCode. Use it to optimise Claude's ability to build, run and...
backbay-labs/clawdstrike
Runtime security enforcement and threat hunting engine for autonomous AI fleets. Build Swarm...