Policy + evidence for everything your AI agent executes. 🦀 Kernel-native sandbox for agent commands & MCP servers — Landlock+seccomp (Linux), Seatbelt (macOS). Tamper-evident, offline-verifiable audit trail. No Docker, no root, one Rust binary. Agent-agnostic.
Latest release v0.1.0-alpha.2 · 30 Apr 2026
2 files for Codex, OpenCode and Claude Code: ClawCrate AGENTS.md, ClawCrate CLAUDE.md — 9,152 tokens loaded in every session.
AGENTS.md A 419 tok CLAUDE.md C 8,733 tok These files are manuelpenazuniga/ClawCrate's own configuration — they tell Codex, OpenCode and Claude Code 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.