开源AI智能体执行治理引擎Rigorix发布
Start here
2026年11月3日,开源AI Agent执行治理引擎Rigorix正式发布。该引擎采用Rust编写且不依赖模型进行强制判定,能够在操作生效瞬间重新验证权限,并生成可供第三方独立验证的签名决策存证。Rigorix提供4道前置检查关卡、本地MCP server以及CLI工具,支持通过Ed25519检查点与哈希链离线审计执行与拒绝记录。目前,其对应验证器已上架crates.io、npm和PyPI。
AI-generated from reports · Updated 16 hours ago
Report timeline
Follow the reports to see different sides of the story.
- Hacker News · AISelectedOpen-Source AI Agent Execution Governance Engine Rigorix Released
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.
Story heat trend
Current heat 6·Comparable peak 10(Nov 3 22:00)·Comparable change, last 24 hours–
Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.