MinerU
by opendatalab · github.com/opendatalab/MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Stars
★ 75k
Forks
6,336
Language
Python
Category
AI Agents
License
NOASSERTION
ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpythonagentllm
Featured in
- MinerU @ 03:28 · Dec 11, 2025