MinerU

Parse PDFs, images, Office documents, and HTML into Markdown using MinerU's document intelligence API.

opendatalab 162 ↓ 348
Claude CodeClaude DesktopGeneric
View source ↗

MinerU parses complex documents into clean Markdown through two tools: document conversion supporting PDF, DOCX, PPTX, XLSX, images, and HTML, and OCR language listing across 109 supported languages. It integrates with MinerU's document intelligence pipeline via optional API token for enhanced precision parsing, and supports both local and streamable HTTP deployment modes.

Source

Repository: https://github.com/opendatalab/mineru-ecosystem

Maintain MinerU?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[MinerU on getagentictools](https://getagentictools.com/mcp/opendatalab-mineru-ecosystem?ref=badge)