Security harness for AI coding agents (Claude Code, Codex CLI, etc.) — mitmproxy payload inspection + TOML policy control.
agent-zoo is a LLM eval & observability project. It focuses on securing and monitoring AI coding agents by inspecting payloads and enforcing policy controls. agent-zoo is an open-source project aimed at AI security engineers. The project is open source (MIT). It ships for the web and the command line.
Behind agent-zoo is ymdarake, and it first shipped in 2026. The project is developed in the open on GitHub with 284 commits in the last 90 days. Key capabilities include payload inspection, policy control, and mitmproxy integration.
What PulseGate has recorded for this listing
Closest matches by what these projects do