Trending repositories: ocr

8 of 8 repositories

• opendatalab/MinerU

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

  AI summary: High-accuracy parsing engine that converts complex documents into LLM-ready Markdown and JSON.

  77,081dataPythonOtherai4sciencedocument-analysisdocxextract-data

• opendataloader-project/opendataloader-pdf

  PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

  AI summary: A high-accuracy PDF parser that extracts AI-ready Markdown, JSON, and HTML using deterministic and hybrid approaches.

  28,188dataJavaApache-2.0a11yaccessibilityaibounding-box

• baidu/Unlimited-OCR

  Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

  AI summary: A system designed for one-shot, long-horizon parsing in OCR tasks.

  22,391ai-mlPythonMITocrdocument-parsingaibaidu

• eigent-ai/eigent

  Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex

  AI summary: An intelligent data extraction and transformation pipeline for unstructured enterprise documents.

  14,783dataTypeScriptApache-2.0agent-frameworkagent-skillsagentic-aiagentic-workflow

• datalab-to/chandra

  OCR model that handles complex tables, forms, handwriting with full layout.

  AI summary: A state-of-the-art OCR model designed to handle complex tables, forms, and handwriting with full layout understanding.

  11,968ai-mlPythonApache-2.0aiocrdocument-intelligencemachine-learning

• run-llama/liteparse

  A fast, helpful, and open-source document parser

  AI summary: A fast, lightweight, and open-source Rust tool for high-quality spatial PDF parsing.

  11,931dataRustApache-2.0document-ocrdocument-processingocrocr-recognition

• xberg-io/xberg

  A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured data from 101 formats (115 file extensions) plus code intelligence for 371 code languages. 15 language bindings — Rust, Python, Ruby, Java, Go, PHP, Elixir, C#, TypeScript — plus CLI, REST API, and MCP server.

  AI summary: High-performance polyglot document extraction framework built in Rust.

  8,910dataRustMITbuncsharpdocument-intelligenceelixir

• deepseek-ai/DeepSeek-OCR-2

  Visual Causal Flow

  AI summary: A state-of-the-art optical character recognition model featuring dynamic resolution and causal flow.

  3,236ai-mlPythonApache-2.0ocrvision-language-modeldocument-parsingpytorch