PhyAgentOS/PhyAgentOS-core

Physical AI runtime for embodied agents — governed action, verified experience, physical memory, and skill evolution.

The Agentic Operating System for Robots

RPent: Agentic Infrastructure for the Physical World

An embodied task agent that connects perception, action, verification, and learning in a continuous physical-world loop

ENPIRE is an agentic framework that allows AI coding agents to autonomously self-improve real-world robot policies through closed-loop physical trial, error, and evolution

A training-free multi-agent framework for recursive self-improvement in new environments through broad-then-deep autonomous exploration and reusable memory.

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

The open-source operating system for physical AI.

RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI