microsoft/markitdown
Python tool for converting files and office documents to Markdown.
Supports 20+ file formats (PDF, Office documents, images, audio, HTML, archives) with modular optional dependencies and preserves document structure like tables and headings. Uses a pluggable converter architecture that streams from file-like objects without creating temporary files, and integrates with LLMs for image descriptions and speech transcription. Includes an MCP server for Claude Desktop integration and optional Azure Document Intelligence backend for advanced layout analysis.
90,677 stars and 3,746,161 monthly downloads. Used by 25 other packages. Actively maintained with 3 commits in the last 30 days. Available on PyPI.
Stars
90,677
Forks
5,354
Language
Python
License
MIT
Category
Last pushed
Mar 10, 2026
Monthly downloads
3,746,161
Commits (30d)
3
Dependencies
6
Reverse dependents
25
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/microsoft/markitdown"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
doocs/md
✍ WeChat Markdown Editor | 一款高度简洁的微信 Markdown 编辑器：支持 Markdown 语法、自定义主题样式、内容管理、多图床、AI 助手等特性
AIDotNet/OpenDeepWiki
OpenDeepWiki is the open-source version of the DeepWiki project, aiming to provide a powerful...
hyperfield/ai-file-sorter
Cross-platform desktop application for content-aware file organization and renaming. Supports...
shoryasethia/markdrop
A Python package for converting PDFs to markdown while extracting images and tables, generate...
drl990114/MarkFlowy
The AI Markdown Editor