1.opendatalab / MinerUTransforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.extract-datalayout-analysisocrparserpdfpdf-converter+10 morePythonOther license83K total6.9K forks+2,057 starsfrom 80,890 · score 7.63
2.docling-project / doclingGet your documents ready for gen AIaiconvertdocumentspdftablesdocument-parser+9 morePythonMIT70K total5.3K forks+1,758 starsfrom 68,212 · score 7.47
3.transmute-app / transmuteSelf hosted file converter and compression tool for images, video, audio, json, excel and more. Supports over 3,000 conversions!convertdockerpythonfile-converterself-hostedaudio-converter+5 morePythonMIT1.5K total103 forks+56 starsfrom 1,401 · score 4.04