OCR & Documents
opendatalab/MinerU-Diffusion
[ECCV 2026] A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding.
PythonMITupdated Jun 18, 2026
🏆 #8 overall#2 of 313 in OCR & Documents🔥 active this week
opendatalab /MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
$ git clone https://github.com/opendatalab/MinerU.gitStars
80.6K
80,582
Forks
6.7K
6,726
Language
Python
License
Other
Created
Feb 29, 2024
2.6 years old
Last push
Sep 24, 2026
🔥 this week
Categories
More in OCR & Documents
OCR & Documents
bytedance/Dolphin
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
PythonOtherupdated Mar 25, 2026
OCR & Documents
DocumindHQ/documind
Open-source platform for extracting structured data from documents using AI.
JavaScriptOtherupdated May 15, 2025
OCR & Documents
pymupdf/PyMuPDF🔥 active
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
PythonAGPL-3.0updated Sep 24, 2026
OCR & Documents
lucasrla/remarks
Extract annotations (highlights and scribbles) from PDF, EPUB, and notebooks marked with reMarkable tablets. Export to Markdown, PDF, PNG, SVG
PythonGPL-3.0updated May 26, 2024
OCR & Documents
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.
PythonApache-2.0updated Sep 16, 2026
Data from GitHub · snapshot Sep 24, 2026