← 返回事件
持续讨论AI

Show HN: Conduct, open-source guardrails for LLM and MCP tool calls

图:Hacker News

发生了什么

AI agent governance for teams. Runtime firewalls tell you what happened; Conduct Guard controls what can happen — signed policy, verified chain, fail-closed by default. Ships with Router (LLM proxy...

摘要按规则整理自下方来源原文

为什么在扩散

来源