MarkItDown is a Microsoft/AutoGen Python utility for converting PDF, Office, HTML, images, audio, and archives into Markdown for LLM pipelines.
Open Source: #markdown
Catalog projects marked with #markdown. Tags work as dedicated landing pages, so related tools are easier to find and connect.
This collection holds 21 projects with a combined 1,362,149 GitHub stars. Main languages: TypeScript, Python, Markdown.
Repositories
Firecrawl is an API and open server for search, crawling, and turning web pages into clean Markdown or structured data.
HowToCook is an open cookbook for programmers, with recipes, ingredients, and step-by-step structure written like clear documentation.
Mermaid is a diagrams-as-code library for flowcharts, sequence diagrams, graphs, C4, Gantt, and other visuals written as text.
Crawl4AI is a Python crawler and web-data extraction tool that prepares pages for LLM, RAG, and agent workflows.
MinerU is a document-analysis tool that turns PDFs and office files into Markdown/JSON for search, RAG, and agent workflows.
Docusaurus is a tool for documentation sites, blogs, and project websites built with Markdown and React.
tldr-pages is a community-maintained collection of short command-line cheatsheets.
Memos is a lightweight Markdown note-taking app that can run on your own server.
Markdown Here is an extension for writing email in Markdown and rendering it to HTML.
MarkText is a desktop Markdown editor with a clean interface and live editing.
Joplin is an open-source note-taking app with Markdown, sync, Evernote import, and clients for desktop and mobile systems.