Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Latest release mineru-4.0.12-released — MinerU 4.0.12 · 11 Oct 2026
2 files for Codex, OpenCode and Claude Code: MinerU AGENTS.md, MinerU CLAUDE.md — 2,387 tokens loaded in every session.
AGENTS.md A 4 tok CLAUDE.md A 2,383 tok These files are opendatalab/MinerU's own configuration — they tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.