• Picks
  • Discover
  • Alternatives
  • About

© 2026 Willet

  • Newsletter
  • About
  • FAQ
  • Terms
  • Privacy & Cookies
Join the Discord (opens in a new tab)
Microsoft avatar

MarkItDown

Converts PDFs, Office files, and other documents into Markdown for LLMs

  • Agent frameworks and tools
  • Productivity
  • Developer tools
View on GitHub

What it is

A Python library and command-line tool that turns PDF, Word, PowerPoint, Excel, HTML, EPUB, images, audio, ZIP archives, and YouTube links into Markdown that keeps headings, lists, tables, and links. Optional extras add OCR, speech transcription, and Azure document services, and third-party plugins can add new formats. Developers building LLM and text-analysis pipelines use it to feed document contents to models in a compact, structured form.

Images

Facts

Stars
191,265 GitHub stars.
191,265

Forks
14,236
Commits
420
Contributors
133
Language
Python
License
MIT
Last commit
Oct 4, 2026
On GitHub since
November 2024
First release
December 2024
Platforms
CLI, library
Self-hostable
No
Tags
  • markdown
  • pdf
  • ocr
  • document-parsing
  • file-conversion
  • rag

Last synced from GitHub on Oct 20, 2026

The 10 best overlooked open-source projects, every Monday.

Share and more

Comments

No comments yet. Start the conversation.

Similar projects

  • Firecrawl avatar

    pdf-inspector

    Rust library that classifies PDFs and extracts their text as Markdown

    19.7k
  • Docling Project avatar

    Docling

    Python library and CLI that converts documents into structured data for AI

    69.2k
  • opendataloader-project avatar

    OpenDataLoader PDF

    PDF parser that outputs Markdown, JSON and HTML, plus PDF auto-tagging

    29.8k
  • LlamaIndex avatar

    LiteParse

    Local PDF and office document parser with OCR and bounding boxes

    12.9k

What people are saying

Updated Oct 20, 2026
  • Hacker NewsMarkItDown: Python tool for converting files and office documents to MarkdownDec 13, 2024 · 329 points · 81 comments (opens Hacker News in a new tab)
  • Hacker NewsPython tool for converting files and office documents to MarkdownJun 11, 2026 · 6 points · 0 comments (opens Hacker News in a new tab)
  • Bluesky“Serendipitously saw this last week, tried it, and it got me most of the way there. For our workload it made more sense to use markitdown[0] -> Luna and we…”Oct 18, 2026 · 1 like · 0 replies (opens Bluesky in a new tab)
  • Bluesky“can you use something like markitdown for that?”Sep 28, 2026 · 0 likes · 1 reply (opens Bluesky in a new tab)
  • Bluesky“Feeding a PDF, Word file or slide deck to an AI? Convert it to Markdown first. pip install 'markitdown[all]' markitdown deck.pptx -o deck.md Microsoft's…”Oct 6, 2026 · 0 likes · 0 replies (opens Bluesky in a new tab)
  • Bluesky“microsoft/markitdown added +771 stars in a day, GitHub's top mover, a 2-year-old repo riding the agent-ingestion wave. pip install 'markitdown[all]' handles…”Sep 8, 2026 · 0 likes · 0 replies (opens Bluesky in a new tab)