mineru

MinerU Skill

An AI-Native document parser built for AI agents — turn PDF, Office & image files into clean Markdown with zero API key, zero install, and fast parallel batches.

中文文档 | English

---

⚡ Try it in 5 seconds (no signup, no token, no pip install)

python3 scripts/mineru.py https://cdn-mineru.openxlab.org.cn/demo/example.pdf --stdout

Prefer uv? The script ships PEP 723 inline metadata, so uv runs it with a managed Python and zero install:

uv run scripts/mineru.py https://cdn-mineru.openxlab.org.cn/demo/example.pdf --stdout

That's it. No account. No API key. No dependencies. The free Agent API parses the PDF and streams clean Markdown straight to your terminal — or to your AI agent.

Need more power? export MINERU_TOKEN=... and the same command auto-upgrades to the Standard API for 200 MB / 200-page files, parallel batches, and DOCX/HTML/LaTeX export.

---

🤔 Why not just call MinerU directly?

	Raw MinerU API / scripts	MinerU Skill
Start with no token	❌ token required	✅ free Agent API, zero-config
Backend selection	🤷 you pick & wire it	✅ auto-routes Agent ⇄ Standard
Install footprint	requests + aiohttp	✅ zero deps (stdlib only)
Agent-friendly output	files only	✅ --stdout Markdown · --json status
Modalities	DIY per format	✅ PDF · image · Word · PPT · Excel · HTML
Batch + resume	hand-rolled	✅ --workers + --resume built in
Bad-token errors	cryptic code None	✅ clear "token expired → refresh here"
Obsidian export	—	✅ --obsidian /path/to/vault

Built for the AI-Agent era: an agent can run it instantly, get Markdown on stdout, and never touch a config file.

---

How MinerU Skill compares

MinerU Skill is not a new parsing engine — it is a zero-config, zero-dependency, agent-native convenience layer over MinerU's cloud API, with 17 turnkey delivery integrations. Its accuracy is whatever MinerU's cloud serves (solid: MinerU2.5 scores 90.67 on OmniDocBench v1.5, MinerU2.5-Pro 95.69 on v1.6). Our edge is DX, AI-nativeness, free token-free start, and delivery breadth — not being the most accurate parser, and not an offline option. If you need offline/air-gapped parsing, top formula or table fidelity, or RAG-native chunking, a competitor below is the better tool.

Comparison matrix

Legend: ✅ yes · ⚠️ partial/qualified · ❌ no. "Same backend" = calls the same MinerU cloud API we do, so OCR/table/formula output is identical to ours (no quality difference between us and those tools).