verl: Volcano Engine Reinforcement Learning for LLMs

OpenClaw-RL: Train any agent simply by talking

slime is an LLM post-training framework for RL Scaling.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.

The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞

Harbor is a framework for running agent evaluations and creating and using RL environments.

"🐈 nanobot: The Ultra-Lightweight OpenClaw"

A benchmark for LLMs on complicated tasks in the terminal

Democratizing Reinforcement Learning for LLMs

🙌 OpenHands: Code Less, Make More

GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.

[COLM 2025] Official repository for R2E-Gym: Procedural Environment Generation and Hybrid Verifiers for Scaling Open-Weights SWE Agents

🤗 smolagents: a barebones library for agents that think in code.

DeerFlow is a community-driven framework for deep research, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.

II-Researcher: a new open-source framework designed to aid building search / research agents

A series of technical report on Slow Thinking with LLM

No fortress, purely open ground. OpenManus is Coming.