microsoft

    microsoft/markitdown

    #47 this week

    Python tool for converting files and office documents to Markdown.

    llm
    documentation
    ai
    autogen
    autogen-extension
    langchain
    markdown
    microsoft-office
    Python
    MIT
    189.1K stars
    14.0K forks
    189.1K GitHub watchers
    Updated Oct 8, 2026
    View on GitHub

    Build with Backblaze B2

    SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.

    Explore Backblaze Labs

    Loading star history...

    Where it stands

    Rank, growth pace and release cadence relative to everything GStars tracks.

    Ranks #4 among LLM repositories tracked this week, and #1 over the last 30 days; #47 of 2,841 repositories GStars tracks this week (top 2%).

    4 releases in the last 90 days, the latest 16 days ago, with 133 contributors on GitHub.

    Peaked at #6 in the weekly ranking the week of Jun 28, its best in the past year.

    Use Cases & Benefits

    • Converts various file formats and office documents into Markdown for use with large language models and text analysis pipelines.
    • Preserves important document structure like headings, lists, tables, and links in Markdown, optimizing for token-efficient LLM consumption.
    • Use for extracting structured Markdown content from PDFs, Word, Excel, and PowerPoint files to feed into AI text analysis workflows.
    • Use for integrating document conversion into Python applications or LLM pipelines with optional plugin and Azure Document Intelligence support.
    • Use for automating transcription and metadata extraction from audio, images, and YouTube videos into Markdown for downstream processing.

    Should you depend on it?

    License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.

    License

    MIT

    Permissive: commercial use, modification and redistribution are allowed with attribution.

    Community files

    • README: present
    • Code of conduct: present

    Watch-outs

    No watch-outs from GStars' checks.

    General guidance from repository metadata, not legal advice. How we score

    From the README

    MarkItDown is a lightweight Python utility for converting various files to Markdown for use with LLMs and related text analysis pipelines. To this end, it is most comparable to textract, but with a focus on preserving important document structure and content as Markdown (including: headings, lists, tables, links, etc.) While the output is often reasonably presentable and human-friendly, it is meant to be consumed by text analysis tools -- and may not be the best option for high-fidelity document conversions for human consumption.

    Markdown is extremely close to plain text, with minimal markup or formatting, but still provides a way to represent important document structure. Mainstream LLMs, such as OpenAI's GPT-4o, natively "speak" Markdown, and often incorporate Markdown into their responses unprompted. This suggests that they have been trained on vast amounts of Markdown-formatted text, and understand it well. As a side benefit, Markdown conventions are also highly token-efficient.

    MarkItDown requires Python 3.10 or higher. It is recommended to use a virtual environment to avoid dependency conflicts.

    Excerpt from the microsoft/markitdown README on GitHub (MIT license). © its authors.Read the full README on GitHub

    Daily snapshots

    Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots

    Jul 14: +656Jul 15: +400Jul 16: +341Jul 17: +102Sep 8: +1,661Sep 9: +398Sep 10: +480Sep 11: +253Sep 12: +503Sep 13: +376Sep 14: +420Sep 15: +388Sep 16: +426Sep 17: +334Sep 18: +294Sep 19: +227Sep 20: +301Sep 21: +100Oct 2: +124Oct 3: +194Oct 4: +214Oct 5: +211Oct 6: +115Oct 7: +273Oct 8: +89

    +23,855 stars over 87 days across 31 snapshot days; best day +1,661 on Sep 8.

    Forks

    14.0K+2.2K

    Open issues

    708-128

    Compared with peers in LLM

    Fastest-growing repositories GStars tracks in this cohort for the week of Oct 4, by 7-day star growth

    microsoft/markitdown compared with LLM repositories by stars, 7-day star growth, health score and last release
    RepositoryStars+7dHealthLast release
    DietrichGebert/ponytail162.8K+7.3K75today
    affaan-m/ECC278.6K+4.2K6412 days ago
    thedotmack/claude-mem100.4K+3.7K75today
    rohitg00/ai-engineering-from-scratch68.7K+3.5K753 days ago
    tashfeenahmed/freellmapi34.7K+2.4K75today
    microsoft/markitdown189.1K+07516 days ago
    Category median100.4K+3.7K75—

    Also by microsoft

    Other repositories from this maintainer that GStars tracks

    Discover Repositories

    Search across tracked repositories by name or description