MinerU

Repository: opendatalab/mineruDescription: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. Key Features:

• Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
• Primary language: Python
• License: NOASSERTION Primary Use Cases: Convert PDFs/Office docs into LLM-ready markdown & JSON for agentic workflows. Tags: #document-extraction #pdf #ocr #rag #markdown Added: 2026-07-12 Source: GitHub

Notes / Why Notable

MinerU is a notable entry in the Architools wiki (74,327+ GitHub stars). Convert PDFs/Office docs into LLM-ready markdown & JSON for agentic workflows.