10 alternatives to MinerU

opendatalab/mineru — Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. (82,533 stars, NOASSERTION, files, analytics, ai).

These are the closest projects in the JustClaw-It index that we serve licence-cleared code from, ranked by relevance and by our code-quality score (1–10, the mean over each repo's graded components: completeness, code quality, deployability, reusability, strategic value). JustClaw-It does not serve code from opendatalab/mineru itself (licence class: unknown), so these alternatives are the licence-cleared route.

The alternatives in detail

• pdfminer/pdfminer.six
  Community maintained fork of pdfminer - we fathom PDF
  score 4.5/10 · MIT permissive · 7,046 stars · 38 components · search them
• microsoft/markitdown
  Python tool for converting files and office documents to Markdown.
  score 7.5/10 · MIT permissive · 192,172 stars · 46 components · search them · alternatives
• stirling-tools/stirling-pdf
  #1 PDF Application on GitHub that lets you edit PDFs on any device anywhere
  score 7.2/10 · MIT permissive · 94,814 stars · 3,000 components · search them · alternatives
• firecrawl/pdf-inspector
  Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
  score 6.3/10 · MIT permissive · 19,718 stars · 86 components · search them
• paddlepaddle/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.
  score 4.8/10 · Apache-2.0 permissive · 91,663 stars · 784 components · search them
• genspark-ai/genoffice
  Free, open-source AI Office suite: Docs, Sheets, Slides, PDF, Markdown and HTML editors with a built-in AI agent, plus a `genoffice` CLI and agent skill so Claude Code, Codex and Cursor can create and edit real .docx/.xl
  score 7.2/10 · Apache-2.0 permissive · 10,779 stars · 1,590 components · search them
• iofficeai/officecli
  OfficeCLI is the first and best Office suite purpose-built for AI agents to read, edit, and automate Word, Excel, and PowerPoint files. Free, open-source, single binary, no Office installation required.
  score 6.1/10 · Apache-2.0 permissive · 32,373 stars · 411 components · search them · alternatives
• datalab-to/marker
  Convert PDF to markdown + JSON quickly with high accuracy
  score 4.6/10 · Apache-2.0 permissive · 40,676 stars · 122 components · search them · alternatives
• boonlai/pi-view
  In-terminal previews for Markdown, code, images, and PDFs in Pi and Oh My Pi, with Quick Open.
  score 7.2/10 · MIT permissive · 4 stars · 19 components · search them
• compdfkit/compdf-self-hosted
  Edit, convert, and transform documents across PDFs, Office formats, HTML, TXT, CSV, RTF, JSON, and images with ComPDF Self-hosted, an open-source PDF platform.
  score 4.6/10 · MIT permissive · 147 stars · 209 components · search them

Licence data: JustClaw-It's per-repo licence policy. Is MinerU still maintained? Check it. Licence details: licence checker. Ranking data from 2026-10-29T06:21:36Z.