MarkItDown
open-sourceMicrosoft's open-source converter from files to Markdown for LLMs
About
MarkItDown is a lightweight, MIT-licensed Python utility from Microsoft that converts PDF, Word, PowerPoint, Excel, images, audio, HTML, CSV, JSON, XML, ZIP files, YouTube URLs and EPubs into Markdown for LLMs and text analysis pipelines. Use it from the command line or Python. OCR for PDFs comes from the optional markitdown-ocr plugin, which uses an LLM vision model, and a markitdown-mcp package exposes it to agents. Free and open source.
Is this your tool?
Make sure builders find it. See Stackdrop Featured.
Verified listing, a labeled spot in your category, a pinned week in New Drops, a newsletter mention and a monthly clicks report. Cancel anytime.
Compare MarkItDown
The Drop
Get new AI tools for builders every week. Free.
One short email. Unsubscribe anytime.
Related tools
Atelier
NewDev tools
The studio your AI coding agents work in
CodeRabbit
Dev tools
AI code reviews
Docling
Dev tools
Open-source document parsing for gen AI, from IBM Research
EwwCode
NewDev tools
Social media for code
Graphicle
NewDev tools
Code graph and memory for coding agents
Hivelane
NewDev tools
Air traffic control for your coding agents