A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding. Topics

An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

A polyglot document intelligence framework with a Rust core. Extract text, metadata, images, and structured information from PDFs, Office documents, images, and 91+ formats. Available for Rust, Pyt…

2026马年春晚魔术计算器应用在线版，免安装，更好用

简悦 ( SimpRead ) - 让你瞬间进入沉浸式阅读的扩展

A standalone version of the readability lib

A high-performance, open-source PDF data extraction tool. 一站式开源高性能数据提取工具，将复杂 PDF 文档转换为 Markdown 和 JSON 格式，使用onnx模型。

A comic app built with Flutter, supporting multiple comic sources.

GLM-OCR: Accurate × Fast × Comprehensive

Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

A Python package for interacting with the MinerU Vision-Language Model.

A GPU cluster manager that configures and orchestrates inference engines like vLLM and SGLang for high-performance AI model deployment.

TCPDF - PHP PDF Library - https://tcpdf.org

Official clone of PHP library to generate PDF documents and barcodes

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7 and MiroThinker-H1, achieve 74.0 and 88.2 on the BrowseComp, respectively.

Python Imaging Library (Fork)

a .NET library that can read/write Office formats without Microsoft Office installed. No COM+, no interop.

MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Research Agents, RAG applications, and training data generation.

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Fast math typesetting for the web.

Convert Word documents (.docx files) to HTML

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-fri…

Create and modify Word documents with Python

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

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

Extract and convert data from any document, images, pdfs, word doc, ppt or URL into multiple formats (Markdown, JSON, CSV, HTML) with intelligent structured data extraction and advanced OCR.