{"slug":"mineru","name":"MinerU","category":"rag-docs","categoryName":"Document parsing & web scraping","audience":["for-ai"],"primary":"for-ai","openClosed":"open","pricing":"open-source","license":"Apache-2.0 + 附加条款","maintained":"yes","officialUrl":"https://opendatalab.github.io/MinerU/","repo":"https://github.com/opendatalab/MinerU","latestVersion":"mineru-4.0.11-released","latestRelease":"2026-10-08","stars":82227,"starsAsOf":"2026-10-22","description":"Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.","descriptionZh":"PDF 转 Markdown/JSON 高精度解析","callMethods":["CLI","API"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["ai4science","document-analysis","docx","extract-data","layout-analysis","ocr","parser","pdf"],"language":"Python","lastPush":"2026-10-11","formerly":null,"packages":[{"registry":"pypi","name":"mineru","url":"https://pypi.org/project/mineru/","versionsUrl":"https://pypi.org/project/mineru/#history","latestVersion":"4.0.11","latestDate":"2026-10-08"}],"recentVersions":[{"version":"mineru-4.0.11-released","date":"2026-10-08","prerelease":false,"url":"https://github.com/opendatalab/MinerU/releases/tag/mineru-4.0.11-released","source":"GitHub Release"},{"version":"mineru-4.0.10-released","date":"2026-09-29","prerelease":false,"url":"https://github.com/opendatalab/MinerU/releases/tag/mineru-4.0.10-released","source":"GitHub Release"},{"version":"mineru-4.0.9-released","date":"2026-09-28","prerelease":false,"url":"https://github.com/opendatalab/MinerU/releases/tag/mineru-4.0.9-released","source":"GitHub Release"},{"version":"mineru-4.0.8-released","date":"2026-09-27","prerelease":false,"url":"https://github.com/opendatalab/MinerU/releases/tag/mineru-4.0.8-released","source":"GitHub Release"},{"version":"mineru-4.0.7-released","date":"2026-09-23","prerelease":false,"url":"https://github.com/opendatalab/MinerU/releases/tag/mineru-4.0.7-released","source":"GitHub Release"}],"alternatives":["pymupdf","paddleocr","ocrmypdf","markitdown","docling","unstructured","stirling-pdf","tesseract"],"stacks":["enterprise-rag-knowledge-base"],"scenarios":["rag-and-documents","enterprise-private-ai"],"problems":["pdf-parser-for-rag"],"reasonZh":"中国强项文档解析（源码可得许可）","sources":["profile","priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/mineru.json","pages":{"en":"https://aimap.page/en/software/mineru/","zh-hans":"https://aimap.page/zh-hans/software/mineru/"}}