Article may be outdated

This article is 7 days old. Some details may have changed since publication.

Hacker News·3 min read·medium

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

S
sudhendra1
Show HN: Conduct, open-source guardrails for LLM and MCP tool calls
AI Summary

Conduct is an open-source tool designed to provide runtime governance and security guardrails for AI agents and LLM tool calls. It allows teams to enforce compliance policies across various AI sessions and development environments using a centralized proxy and CLI.

Why it matters

As AI agents gain the ability to execute code and interact with systems, robust security frameworks are essential to prevent unauthorized actions and ensure compliance with standards like SOC 2 and HIPAA.

Dive DeeperCreate a free account to unlock

Runtime governance for AI agents — one policy enforces across every LLM call, every shell tool, every teammate's AI session.

Two product surfaces, one repo, one policy:

Runtime firewalls like Straiker and Lakera tell you what an agent did . Guard controls what an agent can do — with cryptographic proof.

New here? Start with Discovery mode : read-only visibility into every AI action your team takes for 14 days. No policy to author, nothing to install upstream, no cost. When you're ready to enforce, promote a rule from what Discovery already saw.

git clone https://github.com/sseshachala/conductai cd conductai docker compose up API on http://localhost:8000 (Guard + Router live at /guard/* and /proxy/* ) Canvas UI on http://localhost:3000 Redis worker + Postgres come up in the same stack Point any provider SDK at Router:

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologybusinessstartups

Get smarter about the news

Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.

Create free account

Already have an account? Sign in