THUDM/slime
slime is an LLM post-training framework for RL Scaling.
5775 stars
Python
1 awesome list
AQ-MedAI/MrlX
MrlX: A Multi-Agent Reinforcement Learning Framework
- Stars
- 207
- Forks
- 12
- Commits
- 28
- Language
- Python
- Awesome lists
- 1
Similar repositories
rllm-org/rllm
Democratizing Reinforcement Learning for LLMs
5563 stars
Python
1 awesome list
Gen-Verse/OpenClaw-RL
OpenClaw-RL: Train any agent simply by talking
5433 stars
Python
1 awesome list
astooke/rlpyt
Reinforcement Learning in PyTorch
2275 stars
Python
1 awesome list
keras-rl/keras-rl
Deep Reinforcement Learning for Keras.
5556 stars
Python
1 awesome list
CarperAI/trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
4748 stars
Python
1 awesome list
Tracked growth
2 captures since 2026-05-23
Latest capture 2026-05-31 03:02
Stars history
Total starsCommits history
Default branch commitsMetadata
- Created: 2025-10-17
- First commit: 2025-10-17
- Last pushed: 2026-01-19
- Website: https://aq-medai.github.io/MrlX/
- Archived: no
- Stack detected: —
- License: MIT
AI development signals
No AI development config files detected.