GitHub repo leaderboard by stars, growth rate and activity.
🤗 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.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
SGLang is a high-performance serving framework for large language models and multimodal models.
Production ready toolkit to run AI locally
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!
Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.
A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | 🤗 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 | 165,053 | last pushed 21 hours ago | |
| 2 | The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra | TypeScript | 38,915 | last pushed 1 month ago | |
| 3 | SGLang is a high-performance serving framework for large language models and multimodal models. | Python | 35,728 | last pushed 21 hours ago | |
| 4 | Production ready toolkit to run AI locally | C++ | 10,284 | last pushed 2 days ago | |
| 5 | https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/ | Python | 9,914 | last pushed Yesterday | |
| 6 | Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works! | Python | 9,377 | last pushed 6 months ago | |
| 7 | Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code | Rust | 8,358 | last pushed Yesterday | |
| 8 | The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle. | Python | 7,735 | last pushed 2 months ago | |
| 9 | A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines | Python | 5,686 | last pushed 2 days ago | |
| 10 | A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking. | Python | 3,401 | last pushed 21 hours ago |
All · 11,474