Discover great AI tools
📢 NoticeTool submission bug fixed:Submission works again — send us your favorite AI tools to get featured.
Home / Open Source Radar / RAG & Knowledge / MinerU

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Stars83.9k
Forks7k
LanguagePython
LicenseNot specified
Updated2026-11-18
Last push2026-11-17

About this project

MinerU is an open-source retrieval and knowledge project on GitHub: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. It lives in retrieval and knowledge management, the layer that lets a model answer from your own documents instead of from training data alone. It is maintained by opendatalab and published as a public repository you can read, fork and run yourself.

On GitHub the repository is tagged ai4science, document-analysis, docx, extract-data, layout-analysis, ocr, parser, pdf, pdf-converter and pdf-extractor-llm, which is a fair summary of what it covers. There is normally an ingestion pipeline, an embedding and vector index, and a query layer on top. Most of the engineering effort goes into chunking, ranking and keeping the index fresh as documents change.

It is written mainly in Python and released under no standard SPDX license identifier — the repository uses a custom or modified license, so read it before commercial use. It is actively maintained: the most recent commit landed on November 17, 2026.

To try it, clone the repository and follow its README; that file is the canonical install guide. There is also a project page at https://opendatalab.github.io/MinerU/ for documentation or a hosted demo. Because it runs on your own infrastructure, budget time for environment setup: dependencies, model weights and configuration usually take longer than the first successful run.

Key facts as recorded on GitHub: 83,909 stars; 6,950 forks; primary language Python; last commit on November 17, 2026; topics ai4science, document-analysis, docx, extract-data, layout-analysis, ocr.