Name: THUDM/slime
Rating: 5 (8468 reviews)
Author: THUDM

Git

THUDM / slime

Compare

Python

8.5kstars

1.3kforks

Activity

AI Agents

LLM Infra

ML Frameworks

Repository Trajectory

Trended #9 on daily

February 13, 2026

First tracked on GitTrend

February 13, 2026

Similar Projects

Select up to three alternatives to compare with this repository:

radixark/milesMiles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

2.9k

494

huggingface/ml-intern🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

10.8k

1.2k

microsoft/agent-lightningThe absolute trainer to light up AI agents.

18.1k

1.6k

NVIDIA-NeMo/RLScalable toolkit for efficient model reinforcement

558

elder-plinius/OBLITERATUSOBLITERATE THE CHAINS THAT BIND YOU

8.3k

1.5k

OpenPipe/ARTAgent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!

10.7k

983

Loading README...

Contributors

Git

Languages

Cuda

Shell

10%

Python

88%

About

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

thudm.github.io/slime

Topics

Readme

Activity

8.5kstars(85/day)

1.3kforks

Contributors

Git

Languages

Cuda

Shell

10%

Python

88%