GitHub Open Source Insight
Computed at Sep 10, 2026GitHub repo leaderboard by stars, growth rate and activity.
unslothai
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Python75,889 starslast pushed 2 days agohiyouga
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Python74,658 starslast pushed 3 days agorun-llama
LlamaIndex is the leading document agent and OCR platform
Python52,080 starslast pushed 2 days agoQwenAudio
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Python23,519 starslast pushed 4 months agohuggingface
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python21,642 starslast pushed 2 days agoConardLi
A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
JavaScript14,891 starslast pushed 4 months agobentoml
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
Python12,527 starslast pushed 3 days agoaxolotl-ai-cloud
ludwig-ai
Low-code framework for building custom LLMs, neural networks, and other AI models
Python11,752 starslast pushed 3 days agoflyteorg
Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows.
Go7,425 starslast pushed 2 days ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | unslothai Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more. | Python | 75,889 | — | last pushed 2 days ago |
| 2 | hiyouga Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) | Python | 74,658 | — | last pushed 3 days ago |
| 3 | run-llama LlamaIndex is the leading document agent and OCR platform | Python | 52,080 | — | last pushed 2 days ago |
| 4 | QwenAudio Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability. | Python | 23,519 | — | last pushed 4 months ago |
| 5 | huggingface 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning. | Python | 21,642 | — | last pushed 2 days ago |
| 6 | ConardLi A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval | JavaScript | 14,891 | — | last pushed 4 months ago |
| 7 | bentoml Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud. | Python | 12,527 | — | last pushed 3 days ago |
| 8 | axolotl-ai-cloud Go ahead and axolotl questions | Python | 12,455 | — | last pushed 2 days ago |
| 9 | ludwig-ai Low-code framework for building custom LLMs, neural networks, and other AI models | Python | 11,752 | — | last pushed 3 days ago |
| 10 | flyteorg Dynamic, resilient AI orchestration. Coordinate data, models, and compute as you build AI workflows. | Go | 7,425 | — | last pushed 2 days ago |
All · 11,474