Trevor

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

snare. Honeypot canaries for AI agents. Detect compromised agents via fake credentials that phone home when used.

rampart-action. GitHub Action for Rampart policy linting and coverage benchmarking

rampart-verify. Semantic verification sidecar for Rampart — LLM-powered command classification for AI agent security