A feature-rich command-line audio/video downloader

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

One webpage for every book ever published!

Take potentially dangerous PDFs, office documents, or images and convert them to safe PDFs

Easy token price estimates for 400+ LLMs. TokenOps.

GLM-OCR: Accurate × Fast × Comprehensive

Python utilities for Manubot: Manuscripts, open and automated

Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, etc.). Su…

Convert arxiv papers to markdown

Dockerized PaddleOCR pipeline to convert thousands of PDFs into clean text (GPU/CPU, Windows / OSX/ Linux)