{"data":{"slug":"markitdown","name":"MarkItDown","tagline":"MIT office/PDF/media→Markdown converter for RAG pipelines","category":"agents","categoryName":"AI Agents","url":"https://github.com/microsoft/markitdown","github":"https://github.com/microsoft/markitdown","pricing":"open-source","hook":"MarkItDown is Microsoft file-to-Markdown when you need Office docs, PDFs, and images turned into LLM-ready text.","whatsGood":"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.","theCatch":"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.","addedAt":"2026-09-09","featured":false,"domain":"AI Agents","subSpecialty":"Code Context","subcategory":"Code Context","tags":["self-host","permissive","rag","active","fast-stars"],"capabilities":["convert","rag","office"],"surfaces":["Self-host"],"ecosystem":["Python"],"licenseModel":"OSS/MIT","githubStars":190962,"starsPerWeek":1895,"access":"free","archived":false,"repo":{"createdAt":"2024-11-13","pushedAt":"2026-10-04","license":"MIT","archived":false,"checkedAt":"2026-10-19"}},"related":[{"slug":"claude-code","name":"Claude Code","tagline":"Terminal-first coding agent with deep repository context"},{"slug":"cursor","name":"Cursor","tagline":"The AI-first code editor that understands your codebase"},{"slug":"devin","name":"Devin","tagline":"Autonomous AI engineer for defined engineering tasks"},{"slug":"stagehand","name":"Stagehand","tagline":"AI-native browser automation that mixes code and natural language"},{"slug":"browser-use","name":"Browser Use","tagline":"Open-source framework for LLM-driven browser agents"}],"links":{"self":"/api/gems/markitdown","html":"/gems/markitdown","markdown":"/gems/markitdown.md","category":"/api/gems?category=agents","categoryPage":"/stacks/agents"}}