thomas-villani/all2md

View on GitHub ↗

Convert PDF, Word, PowerPoint, HTML, email & 40+ formats to clean Markdown — and back. Built for LLMs, RAG & Python pipelines, with a built-in MCP server.

27 ★6 forksPythonUpdated 18d ago

What you need to know

A Python library and CLI to convert many document formats (PDF, DOCX, PPTX, XLSX, images, etc.) into clean Markdown, with an MCP interface so AI assistants can convert content.

Install

pip install all2md

Key features

  • Converts multiple document formats to Markdown
  • CLI and library interfaces
  • MCP server wrapper for AI assistants

Best for

Turning office documents and PDFs into Markdown for LLM consumption

Reviewed 2026-08-11

Topics

aiclidocument-conversiondocument-parserdocxepubhtml-to-markdownllmmarkdownmarkitdown-alternativemcpmodel-context-protocolocrpandoc-alternativepdfpdf-to-markdownpptxpythonragtext-extraction
Stars
27★
Forks
6
Language
Python
License
MIT
Created
2025-10-10
Last push
2026-08-18