GitHub repo leaderboard by stars, growth rate and activity.

• PaddlePaddle

  #1PaddlePaddle/PaddleOCR

  Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

  Python89,222 starslast pushed 2 months ago
• opendatalab

  #2opendatalab/MinerU

  Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

  Python79,590 starslast pushed 2 days ago
• EvoScientist

  #3EvoScientist/EvoScientist

  🔬 Harness Vibe Research with Self-evolving AI Scientists

  Python4,739 starslast pushed 2 days ago
• xuzhougeng

  #4xuzhougeng/wisp-science

  Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.

  Rust1,118 starslast pushed 24 hours ago

#	Repo	Language	Stars	30-day trend	Last updated
1	PaddlePaddle PaddlePaddle/PaddleOCR Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.	Python	89,222		last pushed 2 months ago
2	opendatalab opendatalab/MinerU Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.	Python	79,590		last pushed 2 days ago
3	EvoScientist EvoScientist/EvoScientist 🔬 Harness Vibe Research with Self-evolving AI Scientists	Python	4,739		last pushed 2 days ago
4	xuzhougeng xuzhougeng/wisp-science Open-source, local-first desktop AI research workbench for scientific computing with Python/R, MCP bioinformatics tools, SSH/WSL/GPU runtimes, and OpenAI/Anthropic models.	Rust	1,118		last pushed 24 hours ago

All · 11,474