#4 · Primary category： Computer Vision
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Project last updated：08/28/26
GitHub Stars
78.7K
Forks
6.6K
Contributors
99
License
Other
Why we included this project
MinerU turns messy PDFs, scanned pages, and Office files into Markdown or JSON that keeps the reading order and structure intact. It handles layout analysis and OCR, and it extracts tables and figures in the same pass, so the output is genuinely usable when you feed it to an LLM or a retrieval system rather than raw text. Teams building RAG backends or agent workflows that consume real-world files will find the structured output saves them a lot of cleanup. It runs locally with a Python API and a CLI, so you can slot it into existing pipelines without depending on a hosted service. The project is actively maintained and widely adopted, which makes it a dependable choice for production document processing.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
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.
tesseract
Tesseract Open Source OCR Engine (main repository)
ultralytics
Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking