Sandbox your local AI agents so they can read/write only what they need
Agent Safehouse is a macOS sandboxing tool that restricts local AI coding agents to the files and integrations they are allowed to use. It is for developers who want to reduce the damage an agent can cause while preserving normal development workflows. Its catalogue entries help configure or use the sandbox with coding agents.
Latest release v0.12.0 · 7 Sept 2026
3 files for Claude Code, Codex and OpenCode: release, agent-safehouse AGENTS.md, agent-safehouse CLAUDE.md — 1,349 tokens loaded in every session.
AGENTS.md A 1,346 tok CLAUDE.md A 3 tok .agents/skills/release/SKILL.md A 57 tok These files are eugene1g/agent-safehouse's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.