secure multiplexed execution paths for agents - zero trust, zero setup, zero latency.

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

Offline security scanner for AI-agent repos, skills, plugins, and MCP servers.

Open-source firewall for AI agents. Policy engine that audits and controls what OpenClaw, Claude Code, Cursor, Codex, and any AI tool can do on your machine.