MarkItDown
by Microsoft
Converts PDF, Office, HTML, image, audio, and ZIP files into structured Markdown for LLM pipelines, preserving headings, lists, tables, and links.
Skills
Office Document Conversion
Converts PDF, Word, PowerPoint, Excel, EPUB, and HTML files to Markdown while preserving headings, lists, tables, and links.
Image And Audio Extraction
Reads EXIF metadata from images, runs OCR on them, and transcribes speech from WAV and MP3 audio files into Markdown.
MCP URI Conversion
Serves a convert_to_markdown tool over STDIO, Streamable HTTP, or SSE that accepts http, https, file, and data URIs.
Azure Cloud Extraction
Routes conversion through Azure Document Intelligence or Content Understanding for cloud OCR, layout analysis, and field extraction.
Third Party Plugins
Loads third-party converter plugins with --use-plugins and lists installed ones, including LLM-vision OCR from markitdown-ocr.
Related Agents
Docling
Parses PDF, DOCX, PPTX, XLSX, HTML, audio, and image files into a unified DoclingDocument and exports Markdown, HTML, D…
Airbyte Agents
Context layer for AI agents: MCP server and Python SDK giving agents unified access to 50+ business data connectors wit…
Arize Phoenix
Traces, evaluates and debugs LLM and agent applications from an open-source observability platform built on OpenTelemet…
Crawl4AI
Crawls and scrapes web pages into clean Markdown for RAG pipelines, with CSS, XPath, and LLM-driven structured extracti…