Show HN: Conduct, open-source guardrails for LLM and MCP tool calls
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...
Summary
Conduct is an open-source tool designed to provide governance for AI agents, ensuring that only approved actions can be taken. It features runtime firewalls and a fail-closed default setting, making it a crucial resource for teams looking to manage LLM and MCP tool calls securely.
Comments (4 of ) ⌛