OCR & Documents
bytedance/Dolphin
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
PythonOtherupdated Mar 25, 2026
🏆 #376 overall#60 of 318 in OCR & Documents🔥 active this week
SoMarkAI /OXR
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
$ git clone https://github.com/SoMarkAI/OXR.gitStars
3.7K
3,714
Forks
246
246
Language
Python
License
Other
Created
Oct 5, 2026
0.1 years old
Last push
Nov 6, 2026
🔥 this week
Categories
More in OCR & Documents
OCR & Documents
itmisx/deepx-code
deepseek标配coding agent、原生支持模型路由、CodeGraph代码图谱、OCR截图识别、自动上下文压缩、最佳工作模式选择，workflow等功能，从根本上节省Token
GoMITupdated Sep 21, 2026
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
OCR & Documents
opendatalab/MinerU🔥 active
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
PythonOtherupdated Nov 9, 2026
OCR & Documents
tesseract-ocr/tesseract🔥 active
Tesseract Open Source OCR Engine (main repository)
C++Apache-2.0updated Nov 9, 2026
OCR & Documents
hiroi-sora/Umi-OCR
OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。
PythonMITupdated Nov 20, 2025
Data from GitHub · snapshot Nov 9, 2026