Git Stars Git Stars

#grpo Repositories

Discover 27 active open source GitHub repositories tagged with #grpo, accumulating 107,970 total stars (averaging 3,998 stars per project). Leading this topic is modelscope/ms-swift with 16,138 stars.

27
Total Repositories
107,970
Total Stars
3,998
Avg Stars/Repo
1
modelscope/ms-swift

Use PEFT or full-parameter training for CPT/SFT/DPO/GRPO on 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, LLaVA, Phi4, ...) (AAAI 2025).

modelscope
โญ 16,138 Python ๐Ÿ‘ค modelscope Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2023-08-01
2
Orchestra-Research/AI-Research-SKILLs

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

Orchestra-Research
โญ 14,716 TeX ๐Ÿ‘ค Orchestra-Research Organization ๐Ÿ• Updated 2026-10-11 ๐Ÿ“… Created 2025-11-03
3
adongwanai/AgentGuide

AI Agent Development Guide | Agent Harness | Context Engineering | Advanced RAG | MCP | Agentic RL (Reinforcement Learning) | Hands-on LangGraph | 12,000+ LLM Interview Questions | Job Hunting for Algorithm / Development Roles | Switching Careers to LLMs

adongwanai
โญ 12,147 MDX ๐Ÿ‘ค adongwanai User ๐Ÿ• Updated 2026-11-05 ๐Ÿ“… Created 2025-11-03
4
OpenPipe/ART

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

OpenPipe
โญ 10,866 Python ๐Ÿ‘ค OpenPipe Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2025-03-10
5
oumi-ai/oumi

Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!

oumi-ai
โญ 9,441 Python ๐Ÿ‘ค oumi-ai Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2024-05-07
6
om-ai-lab/VLM-R1

Solve Visual Understanding with Reinforced VLMs

om-ai-lab
โญ 6,048 Python ๐Ÿ‘ค om-ai-lab Organization ๐Ÿ• Updated 2026-07-07 ๐Ÿ“… Created 2025-02-06
7
rasbt/reasoning-from-scratch

Implement a reasoning LLM in PyTorch from scratch, step by step

rasbt
โญ 5,885 Jupyter Notebook ๐Ÿ‘ค rasbt User ๐Ÿ• Updated 2026-11-02 ๐Ÿ“… Created 2025-03-04
8
Gen-Verse/OpenClaw-RL

OpenClaw-RL: Train any agent simply by talking

Gen-Verse
โญ 5,750 Python ๐Ÿ‘ค Gen-Verse Organization ๐Ÿ• Updated 2026-05-23 ๐Ÿ“… Created 2026-02-26
9
walkinglabs/hands-on-modern-rl

๐Ÿš€ An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

walkinglabs
โญ 4,936 Jupyter Notebook ๐Ÿ‘ค walkinglabs Organization ๐Ÿ• Updated 2026-10-23 ๐Ÿ“… Created 2026-04-10
10
SkyworkAI/Skywork-R1V

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

SkyworkAI
โญ 3,174 Python ๐Ÿ‘ค SkyworkAI Organization ๐Ÿ• Updated 2026-07-29 ๐Ÿ“… Created 2025-03-15
11
datawhalechina/diy-llm

Covers pre-training data, Tokenizers, Transformers, MoE, distributed training, scaling laws, inference, and alignment. 6 progressive coding assignments for full-stack LLM learning.

datawhalechina
โญ 3,035 Jupyter Notebook ๐Ÿ‘ค datawhalechina Organization ๐Ÿ• Updated 2026-11-20 ๐Ÿ“… Created 2025-11-24
12
langfengQ/verl-agent

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

langfengQ
โญ 2,457 Python ๐Ÿ‘ค langfengQ User ๐Ÿ• Updated 2026-06-09 ๐Ÿ“… Created 2025-03-23
13
Liuziyu77/Visual-RFT

Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuningโ€™

Liuziyu77
โญ 2,283 Jupyter Notebook ๐Ÿ‘ค Liuziyu77 User ๐Ÿ• Updated 2025-10-29 ๐Ÿ“… Created 2025-02-24
14
verl-project/verl-omni

Multimodal RL training framework for diffusion & omni models

verl-project
โญ 1,560 Python ๐Ÿ‘ค verl-project Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-04-21
15
Tencent-Hunyuan/MixGRPO

[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

Tencent-Hunyuan
โญ 1,185 Python ๐Ÿ‘ค Tencent-Hunyuan Organization ๐Ÿ• Updated 2026-07-01 ๐Ÿ“… Created 2025-07-29
16
JudgmentLabs/judgeval

The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.

JudgmentLabs
โญ 1,073 Python ๐Ÿ‘ค JudgmentLabs Organization ๐Ÿ• Updated 2026-11-19 ๐Ÿ“… Created 2024-10-25
17
whitecircle/halo

Halo is an open-source framework built by White Circle for training large language and multimodal models

whitecircle
โญ 868 Python ๐Ÿ‘ค whitecircle Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-08-26
18
Haozhe-Xing/agent_learning

A systematic AI Agent development tutorial covering LLM agents, RAG, tool use, memory systems, multi-agent systems, LangChain, LangGraph, MCP, and agentic RL. | Learn AI Agent Development from Scratch | A systematic, comprehensive, practice-oriented Agent development tutorial | Daily automatic tracking of the latest arXiv papers

Haozhe-Xing
โญ 795 HTML ๐Ÿ‘ค Haozhe-Xing User ๐Ÿ• Updated 2026-10-24 ๐Ÿ“… Created 2026-03-13
19
SUFE-AIFLM-Lab/Fin-R1

Fin-R1 is a large language model for complex financial reasoning developed and open-sourced with the joint efforts of the SUFE-AIFLM-Lab at the School of Statistics and Data Science, Shanghai University of Finance and Economics and FinStep.AI.

SUFE-AIFLM-Lab
โญ 789 ๐Ÿ‘ค SUFE-AIFLM-Lab User ๐Ÿ• Updated 2025-03-27 ๐Ÿ“… Created 2025-03-11
20
ucla-mobility/AutoVLA

[NeurIPS 2025] AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

ucla-mobility
โญ 680 Python ๐Ÿ‘ค ucla-mobility Organization ๐Ÿ• Updated 2026-05-29 ๐Ÿ“… Created 2025-06-14
21
redai-studio/Relax

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

redai-studio
โญ 678 Python ๐Ÿ‘ค redai-studio Organization ๐Ÿ• Updated 2026-11-21 ๐Ÿ“… Created 2026-04-13
22
sail-sg/oat

๐ŸŒพ OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

sail-sg
โญ 678 Python ๐Ÿ‘ค sail-sg Organization ๐Ÿ• Updated 2026-01-29 ๐Ÿ“… Created 2024-10-15
23
Gen-Verse/Open-AgentRL

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

Gen-Verse
โญ 664 Python ๐Ÿ‘ค Gen-Verse Organization ๐Ÿ• Updated 2026-06-12 ๐Ÿ“… Created 2025-10-13
24
turningpoint-ai/VisualThinker-R1-Zero

Explore the Multimodal โ€œAha Momentโ€ on 2B Model

turningpoint-ai
โญ 623 Python ๐Ÿ‘ค turningpoint-ai Organization ๐Ÿ• Updated 2025-03-18 ๐Ÿ“… Created 2025-02-24
25
wendell0218/Awesome-RL-for-Video-Generation

A curated list of papers on reinforcement learning for video generation

wendell0218
โญ 587 ๐Ÿ‘ค wendell0218 User ๐Ÿ• Updated 2026-04-15 ๐Ÿ“… Created 2025-02-13
26
adithya-s-k/FineEnvs

FineEnvs โ€” RL Environments 101: Building and Scaling RL Environments in the Age of LLMs

adithya-s-k
โญ 572 Python ๐Ÿ‘ค adithya-s-k User ๐Ÿ• Updated 2026-11-14 ๐Ÿ“… Created 2026-05-01
27
NVlabs/GDPO

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

NVlabs
โญ 517 Python ๐Ÿ‘ค NVlabs Organization ๐Ÿ• Updated 2026-05-20 ๐Ÿ“… Created 2025-12-09

Frequently Asked Questions

1

What is the most popular #grpo repository on GitHub?

The top ranked open source #grpo project on GitHub is modelscope/ms-swift with 16,138 stars. Use PEFT or full-parameter training for CPT/SFT/DPO/GRPO on 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, LLaVA, Phi4, ...) (AAAI 2025).

2

Which programming languages are most used in #grpo repositories?

Among the top ranked #grpo projects on GitHub, the most common programming languages are Python, Jupyter Notebook, TeX, MDX.

3

How is the #grpo repository ranking calculated?

We track 27 active open source repositories tagged with #grpo (500+ stars), totaling 107,970 stars with an average of 3,998 stars per repository. Rankings update daily from the GitHub API.