{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreicawud2aihbytfzd363qymrg4v6gkfx2xufoircjty5ice45i2hta",
    "uri": "at://did:plc:pgryn3ephfd2xgft23qokfzt/app.bsky.feed.post/3mgjkxgyoutb2"
  },
  "path": "/t/core-rth-ai-control-plane-for-governed-agent-systems/174071#post_1",
  "publishedAt": "2026-03-08T03:11:03.000Z",
  "site": "https://discuss.huggingface.co",
  "tags": [
    "github.com",
    "GitHub - rthgit/CORE-RTH: AI control plane and governed runtime for..."
  ],
  "textContent": "Hi everyone,\n\nI’m sharing **CORE-RTH** , an open-source AI control plane and cognitive kernel for orchestrating governed agent systems.\n\nRepository:\n\ngithub.com\n\n### GitHub - rthgit/CORE-RTH: AI control plane and governed runtime for...\n\nAI control plane and governed runtime for multi-agent systems, tool execution, and real-world automation.\n\nCORE-RTH is designed for scenarios where AI agents do more than chat: they coordinate multiple LLMs, tools, browser automation, messaging channels, and potentially real-world systems such as IoT, robotics, and vehicles.\n\nWhat CORE-RTH focuses on:\n\n  * multi-LLM orchestration\n  * governed tool execution\n  * policy enforcement and safety gates\n  * audit trails for critical actions\n  * browser and messaging bridges\n  * real-world integrations\n\n\n\nWhat makes it different from typical agent frameworks is the focus on **governance** , **auditability** , and **safe execution** when agents interact with infrastructure or physical systems.\n\nI’d especially appreciate feedback on:\n\n  1. positioning the project as an AI control plane / governed runtime\n  2. what examples would make the repo easier to evaluate\n  3. governance patterns people find useful in real agent systems\n\n",
  "title": "CORE-RTH: AI control plane for governed agent systems"
}