Upstar existe aussi en français.

Voir cette page en français

Upstar ranks the fastest-rising GitHub projects every hour, across 69 topics. Browse topics

#pdf-ocr · Dev Tools

PDF & OCR

Read, edit and convert PDFs and scanned documents, from parsers and OCR to document-to-Markdown tools.

This week (Oct 27 – Nov 2), the top-ranked are MiniCPM-OCR (+754), OXR (+1,957) and Xiaomi-OCR-0 (+539). The 113 ranked repos gained 18,953 stars, 15% more than the week before.

Updated Nov 2, 08:31 UTC · ranked every hour from GitHub’s daily star counts

Updated 23 min ago

GitHub topic ↗ (opens in new tab)

This week’s ranking

Showing 50 of 113

How Upstar ranks

  1. 1
    OpenBMB/MiniCPM-OCR Fast, accurate OCR with correctness assessment. TypeScript TypeScript · 754 total New
    Gained in 7 d +754 Score 75.4 Total 754
  2. 2
    SoMarkAI/OXR An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training. Python Python · 2.9k total Spotted at 257 stars
    Gained in 7 d +2k Score 64.0 Total 2.9k
  3. 3
    xiaomi-research/Xiaomi-OCR-0 Xiaomi-OCR-0 Python Python · 651 total
    Gained in 7 d +539 Score 50.9 Total 651
  4. 4
    yjid/kensaku Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access. Rust Rust · 497 total
    Gained in 7 d +497 Score 49.7 Total 497
  5. 5
    IceWhaleTech/filens 📄 Office / PDF / iWork / CAD / 3D / RAW / 360° 🔒 Browser-local preview & conversion 🤖 Agent CLI with OCR, structured text & layout extraction ⚡ Rust + WebAssembly 🧩 Vue 3 integration. Open-source, local-first. Your files, your device. TypeScript TypeScript · 329 total
    Gained in 7 d +327 Score 32.7 Total 329
  6. 6
    scott20201225/marknote-pro 本地优先的结构化 Markdown 笔记与知识工作台。原生集成 Git 版本控制、Draw.io 绘图、GeoGebra 建模、思维导图、KDBX 密码库（含 2FA & SSH 直连）及 PDF 专业批注。| Local-first structured Markdown notes & knowledge base with Git, Draw.io, GeoGebra, MindMap, KDBX & PDF. JavaScript JavaScript · 322 total Mixed signals
    Gained in 7 d +273 Score 27.3 Total 322
  7. 7
    Forward-Future/folio Folio — a simple, clean, open-source PDF reader for Windows TypeScript TypeScript · 262 total New
    Gained in 7 d +262 Score 26.2 Total 262
  8. 8
    datalab-to/indra 1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy Python Python · 1.6k total Spotted at 636 stars
    Gained in 7 d +456 Score 13.6 Total 1.6k
  9. 9
    strugglesky/scrubshot 粘贴一张截图，它找出手机号、身份证、银行卡、Token、地址，一键涂掉。 图片全程留在浏览器里——不上传、不联网、可断网使用。 TypeScript TypeScript · 115 total
    Gained in 7 d +111 Score 11.1 Total 115
  10. 10
    xristosstarnetgames439-del/HuiwenMCP 开源鸿蒙PC应用项目。Qt + OpenHarmony / HarmonyOS PC 文档阅读、编辑与格式转换项目，集成 ArkTS、CEF 浏览器内核、PDFium 与 Python HNP。已支持 PDF/Markdown 双栏预览、同步滚动、PDF 转 Markdown 与最近工作区恢复；规划支持 Word 文档预览与编辑、PDF 编辑、Markdown 编辑、OCR 文字识别及多格式批量转换。源码公开，供学习交流与教学参考，欢迎提交 Issue、通过 PR 贡献代码，共同完善鸿蒙 PC 文档工具。自有代码采用 PolyForm Noncommercial 1.0.0 许可。 C++ C++ · 236 total
    Gained in 7 d +117 Score 10.7 Total 236
  11. 11
    baidu/Unlimited-OCR Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing. Python Python · 30.3k total Low activity
    Gained in 7 d +1.8k Score 10.5 Total 30.3k
  12. 12
    YOLOW92/pagesift Rust web scraper & crawler for AI agents: URLs, PDFs and Office files → clean Markdown/JSON. Firecrawl- and Jina Reader-compatible API, MCP server, Python/Node SDKs. Self-hosted single binary. Rust Rust · 184 total
    Gained in 7 d +93 Score 9.3 Total 184
  13. 13
    storytold/pdfcraft PdfCraft: An open-source PDF reader and editor written by scratch in pure Rust Rust Rust · 19.1k total
    Gained in 7 d +1.2k Score 8.9 Total 19.1k
  14. 14
    groundingpi/GroundingPI A 4B grounding foundation model for physical intelligence. Unifies detection, referring, pointing, OCR, GUI, and layout grounding, achieving SOTA overall across 34 benchmarks and improving robot generalization and data efficiency in controlled evaluations. Python Python · 288 total
    Gained in 7 d +98 Score 7.1 Total 288
  15. 15
    LingCore/WinShun Win顺：免费开源的 Windows 快速搜索启动器。双击 Ctrl，拼音秒搜文件、全文搜索 Word/Excel/PDF、剪贴板历史（代替 Win+V）、对话框搜索、任务栏搜索、插件、AI 助手 MCP。Free Windows search launcher: pinyin file search, full-text search, clipboard history, MCP server. Everything/Listary alternative. C++ C++ · 802 total Spotted at 294 stars
    Gained in 7 d +173 Score 6.9 Total 802
  16. 16
    Lechoung-J/reelpack-alpha Reelpack — 给 AI 的视频理解引擎 / The Video-Understanding Engine for AI · License: FSL-1.1-MIT Python Python · 93 total
    Gained in 7 d +63 Score 6.3 Total 93
  17. 17
    sammyZi/pdf-tools 24 free PDF tools and a document scanner for Android. Kotlin + Jetpack Compose, everything on-device, no ads. Kotlin Kotlin · 61 total
    Gained in 7 d +61 Score 6.1 Total 61
  18. 18
    artcraft-android/pdfcraft-android PdfCraft for Android: An Android native open-source PDF reader and editor written in Rust Rust Rust · 236 total
    Gained in 7 d +68 Score 5.2 Total 236
  19. 19
    Cynthia-wlan9509/offline-game-revival 🎮 AI agent skill that revives shut-down mobile games as fully offline memorial builds — plus a zero-token pipeline that rescues lost game data from screenshots & screen recordings. 停服手游离线化 · 录屏抽帧OCR Python Python · 58 total
    Gained in 7 d +50 Score 5.0 Total 58
  20. 20
    FengZhenfei/carrel Ontology-Augmented Generation for AI agents. Python Python · 681 total
    Gained in 7 d +115 Score 4.8 Total 681
  21. 21
    stockedge/manga-generator 原作から脚本・画像生成・組版・PDF出力まで進める、Codex向け漫画制作ツール JavaScript JavaScript · 160 total
    Gained in 7 d +47 Score 4.4 Total 160
  22. 22
    AGIHunt/blurt The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your other agents. Free, open source, Mac. 口喷鸡：Agent 时代的输入法。 Swift Swift · 210 total
    Gained in 7 d +49 Score 3.9 Total 210
  23. 23
    SpringHgui/papersharp Lightweight, cross-platform .NET renderer that turns HTML + CSS into paged PDF and PNG — no headless browser. hand-written block-flow layout. From HTML to any document. C# C# · 44 total
    Gained in 7 d +36 Score 3.6 Total 44
  24. 24
    KalenHwei/PaperDuet Mirror your translation! A lightweight AI paper translator for Mac and Windows. The original PDF and its translation sit side by side, page for page, with formulas, figures and tables in place. Translates into eight languages with a local model: no sign-in, no fees, and papers stay on your computer. 45 total
    Gained in 7 d +35 Score 3.5 Total 45
  25. 25
    liustack/modlens The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。 TypeScript TypeScript · 4.7k total Healthy
    Gained in 7 d +234 Score 3.5 Total 4.7k
  26. 26
    sgfsd/game-russificator Русификатор игр в одну кнопку: Unity, Ren'Py, RPG Maker. Переводит файлы игры, а любую другую игру (Unreal, Godot) — поверх экрана. Офлайн-переводчик, нейросеть на ПК или по API-ключу. Бесплатно, без регистрации, открытый код. Python Python · 46 total
    Gained in 7 d +33 Score 3.3 Total 46
  27. 27
    cynicalight/NeoRead NeoRead: a local-first EPUB/PDF reader with annotations, side-by-side translation, and AI assistance through Claude Code, Codex CLI, and Kimi CLI. TypeScript TypeScript · 371 total
    Gained in 7 d +58 Score 3.3 Total 371
  28. 28
    virgiliojr94/book-to-skill Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work. Python Python · 36.7k total Healthy
    Gained in 7 d +592 Score 3.1 Total 36.7k
  29. 29
    mg-chao/snow-apps Snow Apps repository, providing source code for Snow Shot and Snow Image Viewer. C++ C++ · 6.5k total Healthy
    Gained in 7 d +236 Score 3.0 Total 6.5k
  30. 30
    nobell001/YES-BD2 Brown Dust 2 (BD2) PC automation tool: daily tasks, map runs, trading, Fiend Hunt. 棕色塵埃2 PC 自動化工具 Python Python · 140 total
    Gained in 7 d +31 Score 3.0 Total 140
  31. 31
    microsoft/markitdown Python tool for converting files and office documents to Markdown. Python Python · 193k total Healthy
    Gained in 7 d +1.3k Score 2.9 Total 193k
  32. 32
    valkia/aramgg_client Windows companion for League of Legends ARAM Mayhem with read-only LCU recommendations, Hextech Augment stats, and in-game OCR overlays. TypeScript TypeScript · 622 total Healthy
    Gained in 7 d +67 Score 2.8 Total 622
  33. 33
    oleost/VisionState Turn your cameras into Home Assistant sensors with a local AI: garage door open/closed, people and cars, water, gas and power meters read by any camera or ESP32-CAM. 100% local, any CPU. Python Python · 188 total
    Gained in 7 d +34 Score 2.7 Total 188
  34. 34
    Tencent/WeVisDoc WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables. Python Python · 512 total
    Gained in 7 d +52 Score 2.4 Total 512
  35. 35
    ere123-dev/bubbles-menu Radial menu for Windows: hold a hotkey, aim at a bubble, release. File converter and screen-to-GIF built in. Радиальное меню для Windows с конвертером файлов и записью GIF. Python Python · 24 total New
    Gained in 7 d +24 Score 2.4 Total 24
  36. 36
    fanyuantaier/wechatauto-replica Windows WeChat automation for Windows (non-web), wxauto replica supporting WeChat 4.x - Windows 微信客户端自动化（非网页版）复刻版 Python Python · 594 total Healthy
    Gained in 7 d +54 Score 2.3 Total 594
  37. 37
    datalab-to/lift Extract structured data from documents quickly and accurately. Python Python · 1.3k total Low activity
    Gained in 7 d +78 Score 2.3 Total 1.3k
  38. 38
    TortoTech/torto Next Generation Ebook Reader Rust Rust · 57 total Healthy
    Gained in 7 d +22 Score 2.2 Total 57
  39. 39
    PDFMathTranslate/PDFMathReader Read scientific documents in your language, in realtime, on any platform. 在任何平台上用您的语言实时翻译和阅读科学文献。 JavaScript JavaScript · 80 total
    Gained in 7 d +22 Score 2.2 Total 80
  40. 40
    motalim-ai/adawat Convert, compress and edit any file while you drag it. A free macOS menu bar app in Arabic and English. | حوّل واضغط وعدّل أي ملف وأنت تسحبه. C# C# · 88 total
    Gained in 7 d +22 Score 2.2 Total 88
  41. 41
    guaguastandup/zotero-pdf2zh PDF2zh for Zotero | Zotero PDF中文翻译插件 Python Python · 8k total Mixed signals
    Gained in 7 d +187 Score 2.1 Total 8k
  42. 42
    paperless-ngx/paperless-ngx A community-supported supercharged document management system: scan, index and archive all your documents Python Python · 47.5k total Healthy
    Gained in 7 d +451 Score 2.1 Total 47.5k
  43. 43
    chrisryugj/kordoc 모두 파싱해버리겠다 — HWP·HWPX·PDF·Office 문서를 Markdown으로. 양식 자동 채우기와 신구대조를 갖춘 CLI·MCP 서버 | Convert Korean documents (HWP, HWPX, PDF, Office) to Markdown — CLI and MCP server with form filling and diff TypeScript TypeScript · 2.9k total Healthy
    Gained in 7 d +109 Score 2.1 Total 2.9k
  44. 44
    sobranie2406/modureader An open-source, cross-platform ebook and PDF reader. Dart Dart · 243 total
    Gained in 7 d +29 Score 2.0 Total 243
  45. 45
    Stirling-Tools/Stirling-PDF #1 PDF Application on GitHub that lets you edit PDFs on any device anywhere TypeScript TypeScript · 95.5k total Healthy
    Gained in 7 d +529 Score 1.7 Total 95.5k
  46. 46
    opendatalab/MinerU Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. Python Python · 83k total Healthy
    Gained in 7 d +480 Score 1.7 Total 83k
  47. 47
    docling-project/docling Get your documents ready for gen AI Python Python · 70k total Healthy
    Gained in 7 d +398 Score 1.5 Total 70k
  48. 48
    happycola233/tchMaterial-parser 国家中小学智慧教育平台 电子课本下载工具，帮助您从智慧教育平台中获取电子课本的 PDF 文件网址并进行下载，让您更方便地获取课本内容。 Python Python · 7.6k total Healthy
    Gained in 7 d +130 Score 1.5 Total 7.6k
  49. 49
    flyfish-dev/file-viewer Preview 275+ file formats in the browser: Office, PDF, OFD, CAD, 3D, archives. Pure frontend, no server conversion. Vue / React / Svelte / Web Components. TypeScript TypeScript · 2.7k total Healthy
    Gained in 7 d +72 Score 1.4 Total 2.7k
  50. 50
    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. Python Python · 92.1k total Low activity
    Gained in 7 d +424 Score 1.4 Total 92.1k
Show more

Emerging in PDF & OCR Past weeks: Oct 26Oct 19