Show HN: Conduct, open-source guardrails for LLM and MCP tool calls
Summary
Conduct introduces an open-source framework for AI agent governance with two surfaces (Guard and Router) and a three-pillar security model (signed configuration, hash-chained audit, policy-first decisions). It also details deployment options (Docker Compose, Kubernetes, hosted offering) and lists 20+ compliance packs and 22 pre-built playbooks for practical workflows.