← Discover
GitHub · microsoft/markitdown↑ +1,410 today

Prepare your documents for artificial intelligence

MarkItDown (Microsoft); It's a lightweight Python tool that converts Word, PDF, PowerPoint, Excel, and more into clean Markdown text that large language models can easily read. Converts while preserving headings, lists, and tables within the document.

Updates

  • October 22, 2026: Stars 187,180 → 191,564, latest release v0.1.9 (October 21, 2026).
  • September 27, 2026: Stars 181,042 → 187,180, latest release v0.1.8 (September 21, 2026).
  • September 8, 2026: Stars 170,726 → 181,042, latest release v0.1.7 (July 29, 2026).
  • August 2, 2026: Stars 128,420 → 170,726, latest release v0.1.7 (July 29, 2026).

What you get

  • It turns your documents into clear texts that artificial intelligence can process.
  • It preserves header, list and table structures.
  • Ideal for your RAG and text analysis processes.

Installation

Install from PyPI (All Features)
pip install 'markitdown[all]'

Running it

Convert file to Markdown
markitdown belge.pdf > belge.md

Example usage

report.pdf · presentation.pptx · table.xlsx

Installation + usage

Paste this into your AI agent (Claude Code · Codex · Antigravity)

Install MarkItDown using the command pip install 'markitdown[all]' in the terminal, then convert a PDF, Word, Excel or PowerPoint file to Markdown by running the command 'markitdown filename.pdf > document.md'.

Repository: https://github.com/microsoft/markitdown. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

PowerPointMarkdownRAGPDFOpen SourceArtificial Intelligence
Who it is forAnyone who will give their documents to AI
DifficultyBeginner–intermediate Python 3.10+
What offersFile → clean Markdown
SupportsWord, PDF, PowerPoint, Excel, visual, audio…
FeeFree · open source (MIT)
License: MIT · You can use it freely, modify it, and use it commercially.

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-05-29: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.