MinerU
CLAUDE.md82k starsChanged 4 months agoLicence not identifiedView on GitHub
使用 uv 管理 Python 虚拟环境和依赖。 运行 Python 代码须在项目根目录 MinerU 中执行： 处理 GitHub issue 时，commit message 和 PR body 中不要使用会导致 issue 在 merge 后自动关闭的关键词。 禁止使用： - fixes #123 / fix #123…
- Installs packages
Trending
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Aug 2026Sep 2026Oct 2026
Who's talking about opendatalab/MinerU
- Fahd Mirza“MinerU 2.5 with vLLM: Extract Data from Any PDF - Easy Tutorial”YouTube · Sep 25, 2025 · 6.8k views
- Fahd Mirza“Install MinerU Locally with GUI for High-Quality PDF Extraction”YouTube · Jan 24, 2025 · 3.9k views
- Forkcast“PDFs are a nightmare for AI, this tool fixes that. #llm #ai #opensource #github #pdf”YouTube · Jul 6, 2026 · 3.6k views
- Isaac Flath“MinerU 4.0: read a passage without loading the full PDF”YouTube · Sep 24, 2026 · 1.3k views
- Alex Hitt“MinerU GitHub by OpenDataLab Tutorial: OCR, VLM, Markdown, and JSON Extraction”YouTube · Jun 28, 2026 · 1.2k views
The biggest 5 of 91 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 91
Talked about on GitHub, YouTube, Bluesky, Hacker News and the web (91 times).
On GitHub · 50
- Sep 28, 2026feat: Support MinerU 4.x V1 API in the built-in MinerU document loader — open-webui/open-webui3 reactions · 4 comments
- Mar 11, 2025gpu环境并发请求：RuntimeError: could not execute a primitive — PaddlePaddle/PaddleOCR3 reactions · 17 comments
- Jul 26, 2026[Feature Request] Add MinerU as an optional PDF parsing backend — jmiba/zotero-redisearch-rag2 reactions
- Jun 12, 2026Update MinerU 3.x Plugin supports file types. — langgenius/dify-official-plugins2 reactions · 1 comment
- Oct 26, 2026Fix OFD inline reading order and prepare 0.6.3 — myhloli/DocVortex1 reaction · 1 comment
45 more on GitHub
- Oct 2, 2026支持 MinerU 4 本地 V1 API：测试连接请求 /health 返回 404 — nashsu/llm_wiki1 reaction
- Aug 14, 2026[enhancement] 支持 MinerU 官方云 API（mineru.net /api/v4）作为后端 — HuanLinOTO/dsh-plugin-mineru1 reaction · 1 comment
- Mar 24, 2026feat(skills): add mineru document extraction skill by mineru official — openclaw/openclaw1 reaction · 2 comments
- Jan 19, 2026[Question]: MinerU backend options — infiniflow/ragflow1 reaction · 3 comments
- Dec 31, 2025[Feature Request]: 可以集合一下minerU的PDF识别功能 — HKUDS/DeepTutor1 reaction · 1 comment
- Jul 19, 2025[Plugin Request]: minerU插件需要升级 ，minerU2本地部署适配问题 — langgenius/dify-plugins1 reaction · 2 comments
- Jul 3, 2025Error while installing with Docker — TechnicolorGUO/InteractiveSurvey1 reaction · 1 comment
- Jun 25, 2025Why is it that the image file generated by the latest compiled MinerU web_api, when used with this plugin, is not uploaded to the Dify knowledge base? — langgenius/dify1 reaction · 2 comments
- Dec 20, 2024PDF Data Extraction — hongbo-miao/hongbomiao.com1 reaction
- Sep 13, 2024Use latest UniMERNet model for Formula Recognition — opendatalab/PDF-Extract-Kit1 reaction · 1 comment
- Oct 28, 2026build(deps): update mineru requirement from <4,>=3.4.1 to >=4.0.12,<5 — gabibenitezzz003/RAG-Anything0 reactions
- Oct 27, 2026chore(deps-dev): update mineru requirement from <4,>=3.2.0 to >=3.2.0,<5 in /backend — zhuzhu1125mango/langchain_rag_demo0 reactions · 2 comments
- Oct 22, 2026Extração e parsing — hoffresearch/urna0 reactions
- Oct 21, 2026Prepare MinerU 4.0.12 with Router review repairs — sjmaple/cr-MinerU0 reactions
- Oct 21, 2026chore(deps): Bump the majors group across 1 directory with 8 updates — lmcdo/nswcompliance0 reactions · 2 comments
- Oct 20, 2026Add 37 catch-up RAG resources (re-land of #2 onto main) — onishimura/awesome-rag-resources0 reactions
- Oct 20, 2026Add 37 approved RAG resources from 2025-26 catch-up — onishimura/awesome-rag-resources0 reactions
- Oct 20, 2026chore(deps): update mineru requirement from <4,>=3.4.1 to >=3.4.1,<5 — P-Bao/ami-multimodal-retrieval0 reactions · 2 comments
- Oct 18, 2026[Feature Request]:Clarify and support MinerU 4.x local parsing compatibility — HKUDS/DeepTutor0 reactions
- Oct 17, 2026chore(deps): bump mineru from 3.4.5 to 4.0.12 — patrickab/gigachad-bot0 reactions · 1 comment
- Oct 14, 2026chore(deps-dev): update mineru requirement from <4,>=3 to >=4.0.12,<5 — OpenBMB/UltraRAG0 reactions
- Oct 14, 2026agent-skills.github.opendatalab.mineru: 4.0.10-released → 4.0.12-released — sudosubin/agents.nix0 reactions
- Oct 14, 2026[M1/P1] Evaluate clause- and table-aware PDF parsing against current pypdf chunker — Dyu20705/student-handbook-utc0 reactions
- Oct 12, 2026Compare source-layout preservation across three document tools — shivamnegi92/awesome-multimodal-extraction0 reactions
- Oct 11, 2026minerU: 4.0.11 -> 4.0.12 — Kh05ifr4nD/coolheaded0 reactions
- Oct 9, 2026whisker: deterministic QA for tomd conversions — cppalliance/wg21-paperflow0 reactions
- Oct 9, 2026minerU: 4.0.10 -> 4.0.11 — Kh05ifr4nD/coolheaded0 reactions
- Oct 7, 2026chore(deps-dev): update mineru requirement from <4,>=3 to >=4.0.10,<5 — OpenBMB/UltraRAG0 reactions · 1 comment
- Oct 3, 2026agent-skills.github.opendatalab.mineru: 4.0.6-released → 4.0.10-released — sudosubin/agents.nix0 reactions
- Oct 1, 2026chore(deps): Bump the majors group with 6 updates — lmcdo/nswcompliance0 reactions · 3 comments
- Oct 1, 2026chore(deps): bump the majors group across 1 directory with 13 updates — lmcdo/nsw-planning-compliance-engine0 reactions · 1 comment
- Sep 30, 2026agent-skills.github.opendatalab.mineru: init at 4.0.6-released — sudosubin/agents.nix0 reactions
- Sep 30, 2026chore(deps-dev): update mineru requirement from <4,>=3 to >=4.0.7,<5 — OpenBMB/UltraRAG0 reactions · 1 comment
- Sep 29, 2026minerU: 4.0.9 -> 4.0.10 — Kh05ifr4nD/coolheaded0 reactions
- Sep 28, 2026minerU: 4.0.8 -> 4.0.9 — Kh05ifr4nD/coolheaded0 reactions
- Sep 28, 2026minerU: 4.0.7 -> 4.0.8 — Kh05ifr4nD/coolheaded0 reactions
- Sep 27, 2026Add fork notice (upstream license and ownership; no upstream changes) — bdickie9/MinerU0 reactions
- Sep 24, 2026minerU: 4.0.6 -> 4.0.7 — Kh05ifr4nD/coolheaded0 reactions
- Sep 23, 2026chore(deps-dev): update mineru requirement from <4,>=3 to >=4.0.4,<5 — OpenBMB/UltraRAG0 reactions · 1 comment
- Sep 22, 2026minerU: 4.0.5 -> 4.0.6 — Kh05ifr4nD/coolheaded0 reactions
- Sep 21, 2026minerU: 4.0.4 -> 4.0.5 — Kh05ifr4nD/coolheaded0 reactions
- Sep 20, 2026minerU: 4.0.3 -> 4.0.4 — Kh05ifr4nD/coolheaded0 reactions
- Sep 19, 2026minerU: 3.4.5 -> 4.0.3 — Kh05ifr4nD/coolheaded0 reactions
- Sep 16, 2026minerU: 3.4.5 -> 4.0.3 — Kh05ifr4nD/coolheaded0 reactions
- Aug 19, 2026chore(deps-dev): update mineru requirement from <4,>=3 to >=3.4.5,<4 — OpenBMB/UltraRAG0 reactions · 2 comments
On YouTube · 22
- Sep 25, 2025MinerU 2.5 with vLLM: Extract Data from Any PDF - Easy Tutorial — Fahd Mirza6.8k views · 16 comments
- Jan 24, 2025Install MinerU Locally with GUI for High-Quality PDF Extraction — Fahd Mirza3.9k views · 11 comments
- Jul 6, 2026PDFs are a nightmare for AI, this tool fixes that. #llm #ai #opensource #github #pdf — Forkcast3.6k views · 5 comments
- Sep 24, 2026MinerU 4.0: read a passage without loading the full PDF — Isaac Flath1.3k views · 2 comments
- Jun 28, 2026MinerU GitHub by OpenDataLab Tutorial: OCR, VLM, Markdown, and JSON Extraction — Alex Hitt1.2k views · 2 comments
17 more on YouTube
- Jul 2, 2026This FREE Tool Turns ANY PDF into Perfect Markdown (MinerU Live Test) — Prompt Engineer 481.1k views · 5 comments
- Jun 26, 2026Turn PDFs Into AI-Ready Markdown — MinerU #github #opensource #coding #ai #developers #shorts — Repo Rundown746 views · 2 comments
- Jun 27, 2026opendatalab/MinerU — Any messy PDF into LLM-ready markdown. 🟢 Clone #Shorts — ForkCast349 views
- Aug 23, 2024GitHub - opendatalab/MinerU: A one-stop, open-source, high-quality data extraction tool, supports... — GitHub Daily Trend AI Podcast303 views
- Mar 13, 2026This repo got 56K stars in 1.9 years 🤯 #MinerU #Pdf #DataExtraction #Ai #Shorts — Pulse298 views · 1 comment
- Oct 2, 2025MinerU2.5: New Preprint Brings LLM Power to PDF Parsing — Bruno Villoutreix’s AI-Biotech-Studio278 views
- Jul 1, 2026MinerU turns any PDF into clean, AI-ready Markdown (open-source, 72k stars) — Marvomatic | AI Automations275 views
- Jun 25, 2026MinerU: Transform Docs for LLMs! — Dann Paker AI118 views
- Jul 6, 2026MinerU: Turn PDFs, Images & Web Pages into Structured Markdown/JSON for AI Agents & RAG — GitRepoOpen83 views
- Jul 28, 2024opendatalab/MinerU - Gource visualisation — Gourcer74 views
- Jun 26, 2026This GitHub Repo Is Trending: MinerU — Repo Radar71 views
- Jul 1, 2026MinerU: The AI That Finally Teaches LLMs to Read PDFs Properly — Praveen Govindaraj67 views
- Jul 4, 2026Stop retyping your PDFs — this free tool does it for you — DEFAULT CURIOUS47 views
- Jul 28, 2026MinerU: Convert Complex Documents Into LLM-Ready Data — BACKFIRED X33 views · 1 comment
- Jun 29, 2026MinerU: 33 Devs, 11 Months. See AI Docs Come Alive! 🌳 — CodeTimelapse32 views
- Jul 2, 2026$0 AI Data Extractor: The RAG Breakthrough [2026] — Repo_AI_Review23 views · 1 comment
- Sep 18, 2026Your AI might be reading your PDF out of order — Urbietisscale11 views
On Bluesky · 15
- Jul 13, 2025A high-quality tool for convert PDF to Markdown and JSON github.com/opendatalab/... #opensource — @cyberciti.biz66 likes and reposts · 1 reply
- Aug 24, 2024PDF、Webサイト、電子書籍などをMarkdownやJSON形式に変換するオープンソースなツール。学術論文などが主なターゲットっぽい？数式や表などもLaTeXに変換してくれるらしい。GPU搭載ならアクセラレーションとして動作可 — @matsuu.bsky.social10 likes and reposts
- Jul 14, 2025🔓 MinerU – a tool that converts PDFs into machine-readable formats. 📦 Supports Markdown, JSON, HTML and more 🌐 mineru.net 📁 GitHub:… — @gitoss.org4 likes and reposts
- Nov 30, 2024🚀 Skyrocketing！ 🚀 (200+ new stars) 📦 opendatalab / MinerU ⭐ 19,199 (+358) 🗒 Python A high-quality tool for convert PDF to Markdown and… — @github-trending.bsky.social4 likes and reposts · 1 reply
- Jan 14, 2025Falls Dir PDF zu langweilig wird 😏 — @netalexx.bsky.social2 likes and reposts · 1 reply
10 more on Bluesky
- Nov 14, 2024🚀 Skyrocketing！ 🚀 (200+ new stars) 📦 opendatalab / MinerU ⭐ 14,601 (+451) 🗒 Python A one-stop, open-source, high-quality data… — @github-trending.bsky.social2 likes and reposts
- Jun 25, 2026🎉 Celebrating！ 🎉 (500+ new stars) 📦 opendatalab / MinerU ⭐ 69,114 (+524) 🗒 Python Transforms complex documents like PDFs and Office… — @github-trending.bsky.social1 likes and repost · 1 reply
- Oct 12, 2025📦 opendatalab / MinerU ⭐ 45,733 (+68) 🗒 Python Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic… — @github-trending.bsky.social1 likes and repost
- Dec 28, 2024📦 opendatalab / MinerU ⭐ 22,191 (+99) 🗒 Python A high-quality tool for convert PDF to Markdown and… — @github-trending.bsky.social1 likes and repost
- Jul 30, 2024今日のGitHubトレンド opendatalab/MinerU MinerUは、PDFからMarkdownへの変換をサポートする、PDF抽出キットに基づいたエンドツーエンドのPDF解析ツールです。… — @dailygithubtrends.bsky.social1 likes and repost
- Jun 26, 20265. MinerU Converts PDFs and Office Docs to LLM-Ready Markdown/JSON LINK 6. General Intuition Raises $320M to Train AI Agents on Gameplay… — @hackobar.bsky.social0 likes and reposts · 1 reply
- Aug 22, 2024🚀 Skyrocketing！ 🚀 (200+ new stars) 📦 opendatalab / MinerU ⭐ 9,300 (+419) 🗒 Python A one-stop, open-source, high-quality data extraction… — @github-trending.bsky.social0 likes and reposts · 1 reply
- Aug 18, 2024🔥 Hot Repo！ 🔥 (100+ new stars) 📦 opendatalab / MinerU ⭐ 8,161 (+178) 🗒 Python A one-stop, open-source, high-quality data extraction… — @github-trending.bsky.social0 likes and reposts · 1 reply
- Aug 1, 2024🎉 Celebrating！ 🎉 (500+ new stars) 📦 opendatalab / MinerU ⭐ 5,074 (+856) 🗒 Python A one-stop, open-source, high-quality data extraction… — @github-trending.bsky.social0 likes and reposts · 1 reply
- Jul 27, 2024🚀 Skyrocketing！ 🚀 (200+ new stars) 📦 opendatalab / MinerU ⭐ 1,923 (+210) 🗒 Python A one-stop, open-source, high-quality data extraction… — @github-trending.bsky.social0 likes and reposts · 1 reply
On Hacker News · 2
- Aug 17, 2024Open-source tool helps you convert PDF documents, web pages, etc., into Markdown61 points · 3 comments
- Aug 3, 2026Transforms complex documents like PDFs and Office docs into Markdown/JSON1 point
On the web · 2
- Jan 28, 2026GitHub - Vastai/MinerU: fork: https://github.com ... — google.com
- Aug 13, 2024PDF to TEXT · Issue #428 · opendatalab/MinerU — google.com
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.