microsoft/markitdown
A Python command-line tool and library that converts PDFs, Word, Excel, PowerPoint, HTML, CSV, JSON, EPUB, ZIP archives and YouTube links into Markdown text. Headings, lists, tables and links are kept, so the output is easier for a model to read.
Idea adaptedKey files read, not run
I learnt this repo's idea and adapted it into my own workspace setup.
How we know
We read the README and key files, not every source file, and did not run it, so the most we can say is Idea adapted or Risky.
Good for
Anyone turning a folder of documents into clean text to feed an LLM or a search index.
Not for
Not for reproducing a document's exact layout; the output is built for model input, and image captions and audio transcription go to outside web services.
Repo
- Stars
- 195,309
- License
- MITUse it, change it, sell it, closed-source included. Keep the author's copyright notice.
- Maturity
- active
- Last push
- 2026-11-07
- Last checked
- 2026-11-14