opendatalab/MinerUπ₯ active
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
OCR engine for all the languages
$ git clone https://github.com/mittagessen/kraken.gitTransforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
The official repo for βDolphin: Document Image Parsing via Heterogeneous Anchor Promptingβ, ACL, 2025.
docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing development and maintenance by t2k.
A Unified Toolkit for Deep Learning Based Document Image Analysis
An Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them into Markdown format. A free alternative to Mathpix, empowering seamless conversion of visual content into text-based representations. 80+ languages are supported.
Data from GitHub Β· snapshot Sep 24, 2026