rllm-org/rllm
Democratizing Reinforcement Learning for LLMs
OpenClaw-RL: Train any agent simply by talking
Democratizing Reinforcement Learning for LLMs
slime is an LLM post-training framework for RL Scaling.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Reinforcement Learning in PyTorch
Official Implementation of "O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL"
A simple yet powerful agent framework that delivers with open-source models
2 captures since 2026-05-25
requirements.txt
· python · 285 dependencies
gui-rl/requirements.txt
· python · 41 dependencies
Megatron-LM/pyproject.toml
· python · 61 dependencies
Megatron-LM/setup.py
· python · 0 dependencies
openclaw-fireworks/requirements.txt
· python · 6 dependencies
slime/pyproject.toml
· python · 3 dependencies
slime/requirements.txt
· python · 17 dependencies
slime/setup.py
· python · 1 dependencies
toolcall-rl/requirements.txt
· python · 3 dependencies
Megatron-LM/uv.lock
· python · 0 dependencies