---
title: "Conduct"
description: "Open-source runtime guardrails that allow, warn, or block every LLM and MCP tool call before it commits, with a hash-chained audit trail."
canonical: "https://vibing.inc/library/conduct-vg-2174"
category: "AI Skills, Agents & MCP"
subcategory: "Agent safety"
license: "Apache-2.0"
author: "@sseshachala"
source: "https://github.com/sseshachala/conductai"
---

# Conduct
Open-source runtime guardrails that allow, warn, or block every LLM and MCP tool call before it commits, with a hash-chained audit trail.
## Facts
- Source: https://github.com/sseshachala/conductai
- Category: AI Skills, Agents & MCP / Agent safety
- Author: @sseshachala
- Licence: Apache-2.0
- Tags: mcp, guardrails, agent-safety, audit, governance
## Why it's a gem
Policy outside the model — compliance packs and audit without trusting prompts.
---
Listed in The Vibeary: https://vibing.inc/library/conduct-vg-2174 · JSON: https://vibing.inc/api/public/library/gems/conduct-vg-2174