{
  "gem": {
    "slug": "conduct-vg-2174",
    "name": "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.",
    "url": "https://github.com/sseshachala/conductai",
    "domain": "github.com",
    "author": "@sseshachala",
    "license": "Apache-2.0",
    "category": "AI Skills, Agents & MCP",
    "subcategory": "Agent safety",
    "tags": [
      "mcp",
      "guardrails",
      "agent-safety",
      "audit",
      "governance"
    ],
    "whyGem": "Policy outside the model — compliance packs and audit without trusting prompts.",
    "sourceType": "github",
    "image": "/api/public/library/og/VG-2174.png",
    "pageUrl": "https://vibing.inc/library/conduct-vg-2174"
  }
}