12,000 stars in six days: anydoc turns Office files and PDFs into clean Markdown
anydoc, an open-source document converter published by the web-scraping company Firecrawl on August 3, has gathered more than 12,000 GitHub stars and 580 forks in under a week. It converts Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV and PDF files into clean Markdown — the plain-text format language models read most reliably. It is written in Rust with Node.js and Python bindings, is released under the permissive MIT licence, and has shipped seven releases since launch, the most recent on August 7.
Why it mattersFeeding documents to a language model is still where most AI projects quietly break: tables collapse into gibberish, headings disappear, and a PDF turns into a wall of text the model reads in the wrong order. A fast, permissively licensed converter that handles the whole office file family is deeply unglamorous infrastructure, and the star count is a measure of how many people had this exact problem. It is a useful reminder that a lot of what makes AI usable is not a model at all.
Read in the app — free, in 9 languages
Related stories
Apple Music will tell you when a song was made by a machine — but the uploader decides whether to say so2026-08-21Rumour: the anonymous model that just topped a coding benchmark, for free, is said to be Zhipu's unreleased flagship
2026-08-21Nvidia is paying $6 billion for the machine that builds a rival's models — and hiring 109 of the people who ran it
2026-08-21Stripe has just paid $7.5 billion for a model router. Days later Ramp built one and is giving it away until January.
2026-08-21Meta's assistant is now a Mac app that reads your screen and types into any window — and what it sees can train the model
2026-08-21