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
- Dev builds MCP layer so Claude Code can work on servers without ever holding SSH keys — NETMESAFE · 2026-10-16
- 'Refusing to code with AI in 2026 is like refusing Google in 2005' — prasenx · 2026-10-16
- Claude Code adds idle compaction to save 1h prompt cache on idle sessions — EricBuess · 2026-10-16
- Handling agents that crash mid-task: the hard part is the unknown outcome across the network — Responsible-Dare5139 · 2026-10-16
- OpenAI DevDay Community Hackathon heads to Berlin with developer, founder and GTM tracks — paw_lean · 2026-10-16
- Data scientist career path is shifting: ML skills no longer enough, AI engineering is the new bar — mdancho84 · 2026-10-16