MarkItDown

by Microsoft

A lightweight utility that converts almost any file into LLM-friendly Markdown.

189.6 k stars GitHub MIT FreeOpen sourceLocal

View on GitHub →

What it does

PDF, Word, PowerPoint, Excel, images, audio, HTML and more
One CLI command or a few lines of Python
Plugins (OCR…) and an MCP server available

Install it

Requirements: Python 3.10+

Install (PDF, DOCX, PPTX formats)

pip install 'markitdown[pdf, docx, pptx]'

Convert a file

markitdown path-to-file.pdf -o document.md

The prompt for your agent

Paste it into your coding agent: it checks the requirements and installs it for you.

Claude CodeCodexCursorGemini CLIopencode

Prompt

Install MarkItDown (https://github.com/microsoft/markitdown) on my machine.
1. Check the requirements: Python 3.10+. If anything is missing, tell me before installing anything.
2. Follow the official method:
- Install (PDF, DOCX, PPTX formats): pip install 'markitdown[pdf, docx, pptx]'
- Convert a file: markitdown path-to-file.pdf -o document.md
3. Check that it works, then explain how to launch it and where to start.

Always review what your agent is about to run, especially install commands.