MarkItDown
Project record
MarkItDown is a Microsoft Python library and command-line tool that converts files such as PDF, Word, PowerPoint, Excel, HTML, images, audio, EPUB, and ZIP archives into Markdown. It aims to keep document structure (headings, lists, tables, links) for use by language models and text analysis pipelines rather than for high-fidelity human-readable conversion.1
- Repository: GitHub repository (external site: github.com)
- Website: PyPI package (external site: pypi.org)
- License: LICENSE (MIT) (external site: github.com)
- Release notes: Release v0.1.8 (external site: github.com)
Availability and license
Overall availability
Source code is public on GitHub and the package is installable from PyPI. Azure-backed converters require the user's own Azure resources.13
Availability is separate from permission: read the license before using or redistributing.
Component reuse rights
- weights
- Unknown — no complete fact-level rights review
- code
- Reviewed qualifying license recorded — check scope and conditions
- data
- Unknown — no complete fact-level rights review
- documentation
- Unknown — no complete fact-level rights review
No complete system-rights review is recorded for this release.
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | Developed in the public microsoft/markitdown GitHub repository.1 |
| DocumentationIs user documentation published? | Public | The README documents installation, command-line and Python usage, optional dependencies, plugins, Azure integrations, and security considerations.1 |
| InstallationAre installation instructions or packages publicly available? | Public | Installable with pip (for example markitdown[all]) or from source; the README also documents building a Docker image.13 |
| Supported platformsAre supported operating systems or hardware documented? | Partial | The README requires Python 3.10 through 3.14, and the PyPI classifiers list CPython and PyPy; supported operating systems are not stated.13 |
| Release statusAre versioned releases published? | Public | Versioned releases are published on GitHub and PyPI; v0.1.8, published on September 21, 2026, was the latest when checked; the first PyPI upload (0.0.1a1) dates from November 2024. PyPI classifies the package as beta.43 |
What it is useful for
Preparing documents as Markdown input for language-model and text-analysis pipelines. The README documents optional per-format dependencies, third-party plugins, an MCP server package (markitdown-mcp), optional image descriptions through an OpenAI-compatible client, and optional conversion through Azure Document Intelligence or Azure Content Understanding, which are billable Azure services.1
Run and use notes
- The README warns that MarkItDown performs I/O with the privileges of the current process and advises sanitizing inputs in untrusted environments and calling the narrowest convert function needed.1
Organization context
U.S. eligibility
Eligible · basis: U.S.-governed project
The repository is in Microsoft's GitHub organization, its MIT license names Microsoft Corporation as copyright holder, and contributions go through the Microsoft Contributor License Agreement. Microsoft Corporation lists One Microsoft Way, Redmond, Washington as its principal executive offices on the cover page of its Form 10-K for fiscal year 2026.215
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.