microsoft/markitdown
Some data may be outdated — see provenance labels.
Python tool for converting files and office documents to Markdown. observed · 2026-10-04
Health v2 · maintenance only
84/100
- Activity 98
- Release rhythm 84
- Longevity 50
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 63.5
- age_days: 706
- days_rel: 29
- days_push: 17
- n_releases_24m: 11
Adoption not part of the score
188214 stars · 13932 forks observed · 2026-10-04
What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-21, confidence 0.98
MarkItDown is a lightweight Python utility that converts a wide range of file types—including PDFs, Office documents, images, audio, and archives—into Markdown. It is designed for text‑analysis pipelines and LLM workflows, preserving structural elements like headings, tables, and links.
Use cases
- Convert a PDF report into Markdown for LLM summarization
- Extract text and tables from Word or Excel files for data analysis
- Generate Markdown from YouTube video transcripts for knowledge bases
- Batch‑process a ZIP archive of mixed documents into a searchable Markdown corpus
- Run OCR on scanned images and output the result as Markdown
When to choose
- You need a simple, Python‑based way to turn diverse document formats into Markdown for downstream AI processing
- Your workflow already uses Python and you prefer a library that can also be invoked from the command line
- Preserving document structure (headings, lists, tables) in a token‑efficient format is important
When to avoid
- You require high‑fidelity visual fidelity or exact layout preservation for human reading
- You need a GUI application or a web service rather than a command‑line tool
- Your environment cannot install Python 3.10+ or the required dependencies
Facets
cli-tool · maturity active
parser file-upload ocr speech-recognition image-processing audio-processing data-science artificial-intelligence python cli cross-platform document-conversion office-files pdf-to-markdown llm-friendly markdown-export natural-language-processing
2 sources
- readme: https://github.com/microsoft/markitdown · fetched 2026-10-04 · 216ef0c07a2a
- registry_pypi: https://pypi.org/pypi/markitdown/json · fetched 2026-09-07 · a54691bc8b60
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| microsoft/markitdown | main | 84 |
For agents
markdown · JSON · MCP: product_card(name="microsoft/markitdown")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem