Upstar classe toutes les heures les projets GitHub qui montent le plus vite, dans 69 thèmes. Voir les thèmes

#pdf-ocr · Outils de dev

PDF & OCR

Lire, modifier et convertir des PDF et des documents numérisés, des analyseurs et de l’OCR aux outils qui les changent en Markdown.

Ce mois-ci (4 oct. – 2 nov.), en tête : pdfcraft (+18 997), OXR (+2 892) et indra (+1 591). Les 258 projets classés ont gagné 85 642 étoiles.

Mis à jour le 2 nov., 10:36 UTC · classé toutes les heures à partir des étoiles quotidiennes de GitHub

Mis à jour il y a 37 min

50 sur 258 affichés

  1. 1
    storytold/pdfcraft PdfCraft: An open-source PDF reader and editor written by scratch in pure Rust Rust Rust · 19,1 k au total
    Gagnées en 30 j +19 k Score 1 577,6 Total 19,1 k
  2. 2
    SoMarkAI/OXR An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training. Python Python · 2,9 k au total Repéré à 257 étoiles
    Gagnées en 30 j +2,9 k Score 289,2 Total 2,9 k
  3. 3
    datalab-to/indra 1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy Python Python · 1,6 k au total Repéré à 636 étoiles
    Gagnées en 30 j +1,6 k Score 159,1 Total 1,6 k
  4. 4
    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++ · 805 au total Repéré à 294 étoiles
    Gagnées en 30 j +805 Score 80,5 Total 805
  5. 5
    OpenBMB/MiniCPM-OCR Fast, accurate OCR with correctness assessment. TypeScript TypeScript · 761 au total Nouveau
    Gagnées en 30 j +761 Score 76,1 Total 761
  6. 6
    FengZhenfei/carrel Ontology-Augmented Generation for AI agents. Python Python · 681 au total
    Gagnées en 30 j +680 Score 68,0 Total 681
  7. 7
    xiaomi-research/Xiaomi-OCR-0 Xiaomi-OCR-0 Python Python · 708 au total
    Gagnées en 30 j +649 Score 64,9 Total 708
  8. 8
    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 · 508 au total
    Gagnées en 30 j +508 Score 50,8 Total 508
  9. 9
    xevrion/gyotaku search every screenshot you've ever taken by the text inside it. native linux, offline, PaddleOCR + sqlite + gpui Rust Rust · 378 au total
    Gagnées en 30 j +376 Score 37,6 Total 378
  10. 10
    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 · 374 au total
    Gagnées en 30 j +374 Score 37,4 Total 374
  11. 11
    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 · 341 au total
    Gagnées en 30 j +339 Score 33,9 Total 341
  12. 12
    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 au total Signaux mitigés
    Gagnées en 30 j +322 Score 32,2 Total 322
  13. 13
    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 · 291 au total
    Gagnées en 30 j +285 Score 28,5 Total 291
  14. 14
    Forward-Future/folio Folio — a simple, clean, open-source PDF reader for Windows TypeScript TypeScript · 263 au total Nouveau
    Gagnées en 30 j +263 Score 26,3 Total 263
  15. 15
    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 au total
    Gagnées en 30 j +236 Score 23,6 Total 236
  16. 16
    artcraft-android/pdfcraft-android PdfCraft for Android: An Android native open-source PDF reader and editor written in Rust Rust Rust · 236 au total
    Gagnées en 30 j +236 Score 23,6 Total 236
  17. 17
    baidu/Unlimited-OCR Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing. Python Python · 30,3 k au total Peu d’activité
    Gagnées en 30 j +3,8 k Score 23,3 Total 30,3 k
  18. 18
    sobranie2406/modureader An open-source, cross-platform ebook and PDF reader. Dart Dart · 243 au total
    Gagnées en 30 j +218 Score 21,8 Total 243
  19. 19
    ss062353-prog/on-device-vision-model On-device Vision Model - a fully offline, free vision pipeline that gives text-only models (e.g. DeepSeek) image understanding and multilingual OCR through an OpenAI-compatible local API. Only tokens are needed: no API key, no subscription, no cloud cost. Recommended for native speakers of Chinese… Python Python · 202 au total
    Gagnées en 30 j +202 Score 20,2 Total 202
  20. 20
    cdcailf/cjkfold Fold look-alike CJK glyphs (Kangxi radicals, CJK radical supplements) so text extracted from PDFs matches again. Python Python · 195 au total
    Gagnées en 30 j +195 Score 19,5 Total 195
  21. 21
    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 · 185 au total
    Gagnées en 30 j +185 Score 18,5 Total 185
  22. 22
    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 · 36,7 k au total En bonne santé
    Gagnées en 30 j +3,3 k Score 18,1 Total 36,7 k
  23. 23
    B0yko/tern Local AI search for podcast and video archives on Apple Silicon: Whisper speech, Apple Vision OCR and SigLIP-2 visual search fused into one ranked list, with a trim editor and FCPXML export. FastAPI, vanilla JS, Tauri. Source-visible, all rights reserved. Python Python · 214 au total
    Gagnées en 30 j +173 Score 17,3 Total 214
  24. 24
    rollroyces/py-idp AI-enabled Intelligent Document Processing for Python: 12+ LLM backends, Pydantic schemas, self-hosted OCR (Nanonets-OCR2-3B), auto-schema discovery, HITL review, prod FastAPI server. AGPL-3.0 + commercial. Python Python · 297 au total En bonne santé
    Gagnées en 30 j +182 Score 17,0 Total 297
  25. 25
    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 au total
    Gagnées en 30 j +169 Score 16,9 Total 210
  26. 26
    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 au total
    Gagnées en 30 j +167 Score 16,7 Total 188
  27. 27
    mg-chao/snow-apps Snow Apps repository, providing source code for Snow Shot and Snow Image Viewer. C++ C++ · 6,6 k au total En bonne santé
    Gagnées en 30 j +1,2 k Score 16,1 Total 6,6 k
  28. 28
    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 au total
    Gagnées en 30 j +160 Score 16,0 Total 160
  29. 29
    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 · 511 au total
    Gagnées en 30 j +250 Score 15,5 Total 511
  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 · 141 au total
    Gagnées en 30 j +141 Score 14,1 Total 141
  31. 31
    microsoft/markitdown Python tool for converting files and office documents to Markdown. Python Python · 193 k au total En bonne santé
    Gagnées en 30 j +5,9 k Score 13,6 Total 193 k
  32. 32
    salikhussain71-code/PAKGOV-RAG-project Research project on bilingual Urdu-English retrieval-augmented generation for Pakistani government and legal documents, with OCR, hybrid retrieval, citation grounding, and evaluation. Python Python · 129 au total
    Gagnées en 30 j +126 Score 12,6 Total 129
  33. 33
    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 au total En bonne santé
    Gagnées en 30 j +234 Score 12,3 Total 594
  34. 34
    PDFCraftTool/pdfcraft PDFCraft is a free, privacy-focused PDF toolkit that runs entirely in your browser. With 90+ professional tools, you can edit, convert, merge, split, and secure your PDF files without ever uploading them to a server. TypeScript TypeScript · 9,7 k au total En bonne santé
    Gagnées en 30 j +1,1 k Score 12,0 Total 9,7 k
  35. 35
    guaguastandup/zotero-pdf2zh PDF2zh for Zotero | Zotero PDF中文翻译插件 Python Python · 8 k au total Signaux mitigés
    Gagnées en 30 j +992 Score 11,8 Total 8 k
  36. 36
    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 · 2,9 k au total En bonne santé
    Gagnées en 30 j +562 Score 11,7 Total 2,9 k
  37. 37
    lona-cn/vision-simple a lightweight C++ cross-platform vision inference library,support YOLOv10/v11/v26、PaddleOCR,using ONNXRuntime with multiple exectuion providers C++ C++ · 223 au total Signaux mitigés
    Gagnées en 30 j +118 Score 11,5 Total 223
  38. 38
    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 au total
    Gagnées en 30 j +115 Score 11,5 Total 115
  39. 39
    jev-chat/jev-chat-jarvis The chat decision assistant: before you reply, Jev reads the chat, judges intent and risk, and drafts replies you fill in with one tap. You press send. Android · Windows · macOS · iOS | 聊天辅助决策工具:先看懂对方再回复,发不发由你。 Kotlin Kotlin · 8,2 k au total
    Gagnées en 30 j +971 Score 11,4 Total 8,2 k
  40. 40
    1003129155/jietuba Open-source Windows screenshot tool with scrolling capture, annotation, OCR, translation, pinned-image editing, GIF recording and clipboard history. 开源 Windows 截图工具:长截图、标注、OCR、翻译、钉图编辑、GIF 录制与剪贴板历史。 C++ C++ · 554 au total En bonne santé
    Gagnées en 30 j +203 Score 10,8 Total 554
  41. 41
    2430816465/campus-knowledge-agent 校园知识服务 Agent 智能体平台:基于 FastAPI、Qwen3 与 RAG,贯通公开资料解析、时间范围检索、证据溯源及人工审核。 Python Python · 108 au total
    Gagnées en 30 j +108 Score 10,8 Total 108
  42. 42
    midagedev/mwoyeo Live, in-place screen translation for macOS — a lens that rewrites the text under it in your language, on-device. Swift Swift · 108 au total
    Gagnées en 30 j +108 Score 10,8 Total 108
  43. 43
    groundingpi/GroundAnything A 4B diffusion grounding model for fast, precise visual evidence extraction. Unifies diverse grounding tasks through parallel decoding, with optional self-speculative decoding delivering 4.51x autoregressive throughput on COCO. Python Python · 109 au total
    Gagnées en 30 j +106 Score 10,6 Total 109
  44. 44
    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 · 4,7 k au total En bonne santé
    Gagnées en 30 j +655 Score 10,3 Total 4,7 k
  45. 45
    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 · 7,6 k au total En bonne santé
    Gagnées en 30 j +842 Score 10,2 Total 7,6 k
  46. 46
    Dai0-2/margino Margino — a browser-native research workspace for Chrome. Read, annotate, ask, remember, and organize papers. TypeScript TypeScript · 96 au total
    Gagnées en 30 j +96 Score 9,6 Total 96
  47. 47
    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 · 96 au total
    Gagnées en 30 j +96 Score 9,6 Total 96
  48. 48
    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 au total
    Gagnées en 30 j +88 Score 8,8 Total 88
  49. 49
    gmi-software/react-native-better-pdf Native, virtualized PDF viewer for React Native, built on Nitro Views Kotlin Kotlin · 88 au total
    Gagnées en 30 j +87 Score 8,7 Total 88
  50. 50
    exuupery/island Island - Dynamic Island for Windows: a liquid pill at the top of the screen with live events, clipboard history, screenshots, a command bar, weather and AI. Free, with a one-time Pro upgrade. 84 au total
    Gagnées en 30 j +83 Score 8,3 Total 84