MarkItDown

knowledgefree tieropen source

Turns PDF, Office and HTML into clean Markdown — the format every LLM digests best.

github.com/microsoft/markitdown

What is it?

A converter that flattens PDFs, Word docs and web pages into plain Markdown text. Like a juicer for documents — whatever fruit goes in, LLM-drinkable juice comes out.

Pricing

Pricing: free
source: https://github.com/microsoft/markitdown · checked 2026-07-09
verified: 2026-07-09