Discover quality open-source projects, submit projects anonymously, and claim and edit your own project.
A little curiosity. A world of open source.
THE FIRST COLLECTIONMinerU is an open-source document parsing engine that converts PDF, images, DOCX, PPTX, and XLSX into structured Markdown/JSON for LLM, RAG, and agent workflows. It supports VLM+OCR dual engines, 109-language OCR, and private/offline deployment.
Docling parses diverse document formats including PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, audio, and more, with advanced PDF understanding, export to Markdown/JSON, OCR, VLM support, and integrations with LangChain, LlamaIndex, and other AI frameworks for RAG and agentic workflows.
A pnpm monorepo providing TypeScript and Go SDKs plus a Node.js CLI for Deckflow's cloud-based deck file processing and task automation APIs.
Zettlr is a privacy-first, open-source publication workbench designed for academic and professional writing, featuring Zettelkasten support and deep integration with reference managers.
An MIT-licensed family of independent TypeScript packages that convert losslessly between OOXML, OpenDocument, Markdown, EPUB, PDF, RTF and legacy formats through one shared Zod schema, with a CLI, MCP server and web UI built on top.
