Pinned Loading

1. OpenClaw-RL OpenClaw-RL Public

   OpenClaw-RL: Train any agent simply by talking

   Python 4.1k 405

2. MMaDA MMaDA Public

   MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion, mixed-CoT, unified RL)

   Python 1.6k 86

3. LatentMAS LatentMAS Public

   Latent Collaboration in Multi-Agent Systems

   Python 818 121

4. ReasonFlux ReasonFlux Public

   [NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

   Python 526 36

5. dLLM-RL dLLM-RL Public

   [ICLR 2026] Official code for TraceRL: Revolutionizing post-training for Diffusion LLMs, powering the SOTA TraDo series.

   Python 468 39

6. Open-AgentRL Open-AgentRL Public

   RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings

   Python 405 48