Minimal native macOS sandbox for Claude and Codex
macOS sandbox-exec guards AI agents so rm -rf can't wreck your whole machine.
Sandbox any macOS app — only your project directory stays accessible
Native macOS sandboxing stops AI agents from reading your SSH keys without Docker overhead.
macOS developers using AI coding agents
Sandboxie · Docker Desktop · OrbStack
I built it because Docker sandboxing requires config and planning. Build in sandboxing of AI tools instead is limited to the very tools themselves, instead I wanted to have a simple cage around Claude running inside VSCode. Also needed to protect files inside a folder like .env.local or keys.
Install via: brew install holtwick/tap/bx
Run like: bx claude .
macOS sandbox-exec guards AI agents so rm -rf can't wreck your whole machine.
direnv auto-activation with bubblewrap sandboxing isolates agents per project.
Git worktrees meet parallel AI sessions in a native macOS window.
Firecracker MicroVMs sandbox agent actions where Copilot Workspace trusts subprocess calls.
Clever launchd scheduling beats cron for maximizing AI token rate limits.
Host-side API key gateway keeps credentials out of agent sandboxes entirely.