rlm

IronClaw is an Agent OS focused on privacy, security and extensibility

Source-available autonomous AI agent with a self-model that actually changes as it runs - ego, affect and identity grounded in real psychology (Higgins, PAD/OCC). Writes its own tools, drives a real browser, runs companies, and grades itself on measured outcomes. Stops before anything it can't take back.

Traffic light for AI Agents and TypeScript/Node multi-agent orchestrator with shared state, guardrails, and adapters for 32 AI frameworks