slime is an LLM training framework for RL Scaling.
Repository Index
72,362 visible repositories in the index
1–3 of 3 · Most stars
OpenClaw-RL: Train any agent simply by talking
- async
- memory-systems
- open-claw
- openclaw-skills
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.