The lightweight framework for building agents

Cutting-edge platform for LLM agent tuning. Deliver RL tuning with flexibility, reliability, speed, multi-agent optimization and realtime community benchmarking.

Scalable RL for Any Agent and Sandbox.

An LLM post-training framework with vLLM for RL Scaling

Agentic RL on Any Harness at Scale

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

The agent that grows with you

Local-first cross-platform desktop workspace for Claude Code / agents: multi-agent, Git worktrees, code diffs, skill marketplace, multi-model, Computer Use, task-aware desktop pets, with WeChat, Fe…

OpenClaw-RL: Train any agent simply by talking

The open source coding agent.

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

SkyRL: A Modular Full-stack RL Library for LLMs

[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning

Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping" by Zhiheng Xi et al.

Tongyi Deep Research, the Leading Open-source Deep Research Agent

[ICLR 2026] Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

Bridge Megatron-Core to Hugging Face/Reinforcement Learning

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings

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

A high-throughput and memory-efficient inference and serving engine for LLMs

Scalable toolkit for efficient model reinforcement

Agentic RL Training at Scale

Muon is an optimizer for hidden layers in neural networks

Unleashing the Power of Reinforcement Learning for Math and Code Reasoners

Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling

Democratizing Reinforcement Learning for LLMs

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.