Open-Source AI Agent Execution Governance Engine Rigorix Released
Show HN: Rigorix, Execution governance for AI agents, open-source engine
Rigorix, an open-source execution governance engine for AI agents, has been officially released. It re-verifies permissions at the exact moment an action takes effect and generates signed decision receipts that can be independently audited by third parties. Written in Rust without relying on models for enforcement decisions, the engine features four pre-execution checkpoints, a local MCP server, and a CLI tool. Corresponding validators are available on crates.io, npm, and PyPI, supporting offline auditing of execution and rejection logs via Ed25519 checkpoints and hash chains.
The project demonstrates real-time permission re-verification during the window between an agent receiving authorization and its actual execution, offering a verifiable, model-free audit trail for high-risk operations.
Source:Hacker News · AI · rigorix.eu