53 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Open WebUI | 1.3M | |
| Yet Another Document Translator | 68K | |
| Your AI second brain. Self-hostable. Get answers from the web or your docs. Buil... | 61K | |
| MCP server for Google search and page fetching using headless Chromium | 4K | |
| Structured text extraction framework for digital and scanned PDFs with inline fo... | 4K | |
| MCP server that provides computer control capabilities, like mouse, keyboard, OC... | 4K | |
| Computer vision, OCR, and input automation toolkit | 4K | |
| Kotones Auto Assistant(kaa) is a script for game 'Gakuen Idol M@ster' that autom... | 3K | |
| Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like... | 2K | |
| Kingsoft Cloud Agent Development Kit - 支持 LangChain/LangGraph/DeepAgents/ADK/Ope... | 2K | |
| Kotonebot is game automation library based on computer vision technology, works ... | 2K | |
| AI Translation Framework - CLI tool for batch translation. | 1K | |
| End-to-end Optical Music Recognition (OMR) system build on top of vision transfo... | 1K | |
| A professional spider tools package | 1K | |
| 视频翻译工具，擅长将非中文视频翻译成中文视频 | 1K | |
| DISK (Domain Incremental conStruction of Knowledge graph) - A tool for distillin... | 944 | |
| Question answering for local knowledge bases with exact source citations. | 933 | |
| AI-native programming language for deterministic, inspectable applications. | 884 | |
| FlexiData is an open-source Python package designed for processing unstructured ... | 720 | |
| 基于 RapidOCR 的高性能本地 OCR 技能 | 702 | |
| Enhanced MCP server for computer control: mouse, keyboard, screenshots, OCR, UI ... | 687 | |
| 625 | ||
| Automatically redacts sensitive data in screenshots before sending to AI agents | 594 | |
| The web version of RapidOCR | 582 | |
| DocTranslater — PDF translation with layout preservation and multi-provider LLM ... | 567 | |
| Production-ready document parsing with Vision Language Models | 489 | |
| Auto-compress PDFs and screenshots to Markdown before they hit Claude Code's con... | 432 | |
| HUI2 is an advanced Android automation library that combines the power of uiauto... | 288 | |
| 286 | ||
| Add your description here | 240 | |
| AI browser agent that costs 50x less. DOM + OCR + Memory. Works with any LLM. | 206 | |
| RAGFast is a LLM Framework for building RAG Application with ease of code. | 200 | |
| A comprehensive text extraction tool supporting multiple file formats | 150 | |
| A CLI-based hard fork of AiNiee for batch translation. | 146 | |
| A versatile OCR and document processing command-line tool. | 142 | |
| BabelDOC fork with enhanced UI integration support (adds --log-progress) | 139 | |
| A simple OCR SDK based on RapidOCR and Flask | 139 | |
| OCR-powered Python library to auto-generate personalized certificates from templ... | 123 | |
| Tools of extracting PDF content based on RapidOCR | 114 | |
| This patch includes several improvement to RAGs, summarizers, downloders and ret... | 114 | |
| LOOP Chat | 105 | |
| MCP server that provides computer control capabilities, like mouse, keyboard, OC... | 97 | |
| 智能笔记助手 CLI | 94 | |
| MCP server that provides computer control capabilities, like mouse, keyboard, OC... | 84 | |
| MCP server that provides computer control capabilities, like mouse, keyboard, OC... | 76 | |
| Open WebUI steve | 73 | |
| A screenshot tool that automatically copies extracted text to clipboard | 71 | |
| convert GIS WMTS tile image to polygon and point using computer vision | 68 | |
| 有赞文档处理 SDK - 支持多格式文档加载与切分 | 61 | |
| A package for Pensieve (previously known as memos) | 57 |
