MarkItDown
MIT office/PDF/media→Markdown converter for RAG pipelines
AI Agents / Code Context · OSS/MIT · 191k
Reviewed 2026-09-09 · last push 2026-10-04 · repo checked 2026-10-19
What's Good
MIT. Python library and CLI. Converts Word, Excel, PowerPoint, PDF, HTML, images (with OCR/vision), audio (with speech-to-text), and more into clean Markdown. Pluggable architecture for custom converters. Azure Document Intelligence and LLM integrations for harder formats. Ideal for RAG ingestion and agentic file processing.
The Catch
Vs files-to-prompt/Repomix/Gitingest (code-context tools): MarkItDown is the *document converter*, not a codebase packer. Heavy formats (PDF, images, audio) need optional dependencies (pdfminer, speechrecognition, Azure services). Quality varies by source format — complex PDFs may need the vision/Azure path.
Verdict
MIT document converter. Free forever; use when agents need to read Office and PDF, not just code.
Embed
Maintainer? Add the badge to your README. It is free, links to this review, and there is no paid version.
Markdown
[](https://stackgems.com/gems/markitdown)
HTML
<a href="https://stackgems.com/gems/markitdown"><img src="https://stackgems.com/badge/markitdown.svg" alt="MarkItDown reviewed on Stack Gems" height="20"></a>