// Read docs & web pages
MinerUmineru-4.0.11-released
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Open source Maintained For agents
IN ONE PARAGRAPH
MinerU is transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to read docs & web pages.
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it from the official package registry:
pip install mineru - 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side → PyMuPDF PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents. ★ 11k PaddleOCR Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages. ★ 91k OCRmyPDF OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched ★ 35k MarkItDown Microsoft tool converting office documents to Markdown for LLMs. ★ 191k docling Get your documents ready for gen AI ★ 69k
03Related
Versions, why it is listed, for AI to read
Recent releases
- mineru-4.0.11-released 2026-10-08
- mineru-4.0.10-released 2026-09-29
- mineru-4.0.9-released 2026-09-28
- mineru-4.0.8-released 2026-09-27
- mineru-4.0.7-released 2026-09-23
For AI agents
- Interfaces：CLI · API
- Machine-readable record：/api/v1/software/mineru.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22