I spent the last 20 years building enterprise software and cybersecurity tools. Last year I started using AI agents for real work — and got terrified. Every tool I tried would happily `rm -rf /` if you phrased it right. One popular agent literally tried to exfiltrate SSH keys (you might have seen that HN post).

So I built Core Rth. It's not a chatbot wrapper. It's a Sovereign Cognitive Kernel — an AI backend where every LLM action is a proposal that must survive a governance layer (The Guardian) before it touches your filesystem, your network, or your hardware.

Here's the thing that makes it different from OpenClaw and friends: Core Rth was designed from day one to control physical systems (IoT via Home Assistant, robots via ROS2, drones via MAVLink). When your AI can actuate a robotic arm or fly a drone, "move fast and break things" is not an option. So we built a Global E-Stop — a hardware kill switch in the Web UI that severs all physical agency instantly.

What's under the hood:

- Guardian: proposal-first governance. No destructive action runs without consent. Ever. - Security Vault: AES-256-GCM encrypted credentials, OS keyring only, zero plaintext keys. - AI Village: parallel agents (Architect, Critic, Synthesizer) debate on a Knowledge Graph before answering. - Model Router: mix OpenAI + Anthropic + local Ollama/vLLM. Route by task type, cost, or privacy. - Mission Control: real-time Web UI with bridge telemetry, policy ledger, and the big red E-Stop.

Try it:

    git clone https://github.com/rthgit/CORE-RTH.git
    cd CORE-RTH
    pip install -r requirements.txt
    python scripts/run_core_rth_local_bench_api.py
    # Open http://127.0.0.1:18030/ui/

I built this because I needed an AI system I could actually trust with my infrastructure. If you're an engineer or CTO who feels the same way, I'd love your feedback on the architecture.

GitHub: https://github.com/rthgit/CORE-RTH

Created by Christian Quintino De Luca — [email protected]