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

Conduct is an open-source governance platform that enforces security policies across LLM and MCP tool calls through two components: Conduct Guard, a policy engine that decides whether to block, warn, audit, or inject actions before execution, and Conduct Router, an LLM proxy that works with any provider SDK. Unlike observability-focused runtime firewalls, Conduct provides cryptographic proof of policy enforcement through signed configuration, a hash-chained audit log, and fail-closed-by-default protection across LLM calls and shell tools.