InfraAug 29, 2026 · 02:29
Show HN: Conduct, open-source guardrails for LLM and MCP tool calls
From github.com
Conduct is an open-source guardrail system for AI agent governance that includes runtime firewalls and signed policy controls. It ships with a Router LLM proxy and is fail-closed by default.
Read the sourceSign in to suggest
Sources
+ 1 more
- DISCUSSIONsudhendra1news.ycombinator.com
#open-source#llm#mcp#agent#safetyMarkdown
Content history (1)
- 2026-10-04 · Summary · vi · Wording fixConduct giúp các đội ngũ quản trị AI agent hiệu quả hơn. Trong khi Runtime firewalls ghi …Conduct giúp các đội ngũ quản trị AI agent hiệu quả hơn. Trong khi Runtime firewalls ghi …
One ranked edition, every morning
The stories that matter today. Free, cancel anytime.
Telegram @aidr_today