AIHacker Newsabout 3 hours ago
Conduct: Open-Source Guardrails for LLM Tool Calls
1 min read
Conduct is an open-source runtime governance system for AI agents, enforcing policies across LLM calls, shell tools, and MCP invocations. It ships with a Router proxy, 20+ compliance packs, 22 playbooks, and a hash-chained audit log. The project is Apache 2.0 licensed.
Level
Hype check
Tap to vote and see what everyone thinks.
Summary by ByteBrief
