GitHub Open Source Insight
Computed at Sep 10, 2026GitHub repo leaderboard by stars, growth rate and activity.
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Go180,490 starslast pushed 2 days agohuggingface
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Python165,014 starslast pushed 2 days agolobehub
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
TypeScript82,334 starslast pushed 2 days agomindsdb
The unified workspace where open-source models get things done for you.
Makefile39,716 starslast pushed 2 days agosgl-project
SGLang is a high-performance serving framework for large language models and multimodal models.
Python35,666 starslast pushed 2 days agoFlashML-org
FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently.
Python12,173 starslast pushed 2 days agoxorbitsai
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
Python9,555 starslast pushed 3 days agoCommandCodeAI
Command Code AI — the best coding agent for open models.
—3,900 starslast pushed 4 weeks agocixingguangming55555
lightseekorg
TokenSpeed is a speed-of-light LLM inference engine.
Python2,105 starslast pushed 2 days ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | ollama Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models. | Go | 180,490 | — | last pushed 2 days ago |
| 2 | huggingface 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. | Python | 165,014 | — | last pushed 2 days ago |
| 3 | lobehub 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team. | TypeScript | 82,334 | — | last pushed 2 days ago |
| 4 | mindsdb The unified workspace where open-source models get things done for you. | Makefile | 39,716 | — | last pushed 2 days ago |
| 5 | sgl-project SGLang is a high-performance serving framework for large language models and multimodal models. | Python | 35,666 | — | last pushed 2 days ago |
| 6 | FlashML-org FreeToken brings datacenter-scale model serving to your desktop. Run massive models locally, fast and efficiently. | Python | 12,173 | — | last pushed 2 days ago |
| 7 | xorbitsai Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API. | Python | 9,555 | — | last pushed 3 days ago |
| 8 | CommandCodeAI Command Code AI — the best coding agent for open models. | — | 3,900 | — | last pushed 4 weeks ago |
| 9 | cixingguangming55555 和国产大模型相关的免费工具集 | JavaScript | 2,523 | — | last pushed 7 months ago |
| 10 | lightseekorg TokenSpeed is a speed-of-light LLM inference engine. | Python | 2,105 | — | last pushed 2 days ago |
All · 11,474