Core Rth
p/core-rth
The AI agent platform that asks before it acts.
•0 reviews•2 followers
Start new thread
trending
Christian Quintino De Luca•

19h ago

Governed agentic AI: proposal-first execution + audit + routing

I m Christian (RTH Italia). I m launching Core Rth (RC1) a governed AI Control Plane for multi-LLM orchestration, tools, channels, and physical bridges.

The core idea is simple: AI proposes Guardian audits Owner approves execution happens.
No silent autonomy , no hidden side effects.

What s included in RC1:

  • Multi-LLM routing (cost/latency/privacy aware) + route explain

  • AI Village (role council: researcher/coder/critic/synth) with live run + synthesis

  • Guardian with policy DSL + severity profiles + audit trail

  • Security Vault (AES-256-GCM): secrets are fetched just-in-time for execution; the model never sees tokens

  • Browser Swarm (Playwright + safe fallback) with SSRF protections

  • Omni-channels (Telegram / WhatsApp / Mail) with replay-safe testing

  • Reality bridges (IoT/Robotics/Vehicles) with safety interlocks + emergency endpoints

Christian Quintino De Luca•

13h ago

Core Rth - The AI agent platform that asks before it acts.

Core Rth is a governed AI assistant you run locally. Like OpenClaw, it connects to WhatsApp, Telegram, Email, and Discord — but every action the AI proposes must survive a governance layer before execution. Built for engineers who automate physical systems (IoT, robotics, drones) and can't afford hallucinating agents with root access.