Microsoft open-sources MarkItDown, a Python tool for turning documents into Markdown
mdancho84 · x · 2026-07-28
Microsoft released MarkItDown, a lightweight open-source Python library that converts PDFs, Office files, images, audio, HTML, and text-based formats into Markdown for LLM pipelines.
The project emphasizes preserving document structure, and the repo screenshot also shows a new MCP server for integration with apps like Claude Desktop. Its inputs include PDF, PowerPoint, Word, Excel, images with EXIF/OCR, audio with transcription, HTML, CSV/JSON/XML, ZIP files, and more. The output options include file output, pipe output, API response, plain text, metadata, and LLM descriptions.
Related event: Microsoft Open-Sources MarkItDown for LLM Document Prep(2 posts)→
More from coding & agent
- CompAI says an AI browser agent can now log in and collect audit evidence — JosephJacks_ · 2026-07-29
- Yangqing Jai Teases New Venture: An AI Oracle to Mass-Produce Systems — jiayq · 2026-07-29
- The missing layer is not code generation, but autonomous software design and upkeep — jiayq · 2026-07-29
- AI could make custom software far more common and change software economics — jiayq · 2026-07-29
- Models write code fast, but production-ready software still needs another layer — jiayq · 2026-07-29
- An autonomous coding system built a database engine and passed 6 million SQLite tests — jiayq · 2026-07-29