GitHub Open Source Insight
Computed at Sep 11, 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.
Go180,608 starslast pushed 3 hours agovllm-project
A high-throughput and memory-efficient inference and serving engine for LLMs
Python91,451 starslast pushed 45 minutes agounslothai
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
Python76,004 starslast pushed 36 minutes agohiyouga
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Python74,699 starslast pushed 2 days agomudler
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Go49,046 starslast pushed 10 hours agoAider-AI
aider is AI pair programming in your terminal
Python48,888 starslast pushed 4 months agoAstrBotDevs
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Python40,348 starslast pushed 8 hours agochatchat-space
Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain
Python38,628 starslast pushed 10 months agosgl-project
SGLang is a high-performance serving framework for large language models and multimodal models.
Python35,790 starslast pushed 34 minutes agolyogavin
AirLLM 70B inference with single 4GB GPU
Jupyter Notebook34,090 starslast pushed 22 hours 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 | 180,608 | last pushed 3 hours ago | |
| 2 | vllm-project A high-throughput and memory-efficient inference and serving engine for LLMs | Python | 91,451 | last pushed 45 minutes ago | |
| 3 | 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 | 76,004 | last pushed 36 minutes ago | |
| 4 | hiyouga Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024) | Python | 74,699 | last pushed 2 days ago | |
| 5 | mudler LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required. | Go | 49,046 | last pushed 10 hours ago | |
| 6 | Aider-AI aider is AI pair programming in your terminal | Python | 48,888 | last pushed 4 months ago | |
| 7 | AstrBotDevs AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨ | Python | 40,348 | last pushed 8 hours ago | |
| 8 | chatchat-space Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain | Python | 38,628 | last pushed 10 months ago | |
| 9 | sgl-project SGLang is a high-performance serving framework for large language models and multimodal models. | Python | 35,790 | last pushed 34 minutes ago | |
| 10 | lyogavin AirLLM 70B inference with single 4GB GPU | Jupyter Notebook | 34,090 | last pushed 22 hours ago |
All · 11,658