agent-chaperone/agent-chaperone

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they execute.

Hooking implementations and supporting tools for various coding agents (Claude, Cursor, Gemini, etc)

Universal security guardrails and workflow policies for AI coding agents.

Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya), allow/review/block

Security layer for AI coding agents. Works with Claude Code, Cursor, Windsurf, Gemini CLI, OpenCode, Pi Agent and more.

Static security scanner for AI agents. Catches prompt injection, runaway loops, missing oversight, and compliance gaps across 21 frameworks. Use from Claude Code, Cursor, ChatGPT (MCP), the CLI, or GitHub Actions.

Auto mode for every coding agent, built on Jev: risk-scores every tool call with session context (deny / ask / allow), flags prompt injection in results, checks skills and plugins. Claude Code, Codex, Copilot, Gemini, Cursor, pi, OpenCode, ACP.

A measured tool-call firewall for AI agents: allow, ask or deny before the agent acts. Claude Code mod and hook, MCP proxy. Built on TypeSafe Jev, measured on real sessions with a blind second labeler.

ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.