#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
Classement du mois
- 1storytold/pdfcraft PdfCraft: An open-source PDF reader and editor written by scratch in pure RustGagnées en 30 j +19 k Score 1 577,6 Total 19,1 k
- 2SoMarkAI/OXR An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.Gagnées en 30 j +2,9 k Score 289,2 Total 2,9 k
- 3datalab-to/indra 1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracyGagnées en 30 j +1,6 k Score 159,1 Total 1,6 k
- 4LingCore/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.Gagnées en 30 j +805 Score 80,5 Total 805
- 5OpenBMB/MiniCPM-OCR Fast, accurate OCR with correctness assessment.Gagnées en 30 j +761 Score 76,1 Total 761
- 6FengZhenfei/carrel Ontology-Augmented Generation for AI agents.Gagnées en 30 j +680 Score 68,0 Total 681
- 7xiaomi-research/Xiaomi-OCR-0 Xiaomi-OCR-0Gagnées en 30 j +649 Score 64,9 Total 708
- 8yjid/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.Gagnées en 30 j +508 Score 50,8 Total 508
- 9xevrion/gyotaku search every screenshot you've ever taken by the text inside it. native linux, offline, PaddleOCR + sqlite + gpuiGagnées en 30 j +376 Score 37,6 Total 378
- 10cynicalight/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.Gagnées en 30 j +374 Score 37,4 Total 374
- 11IceWhaleTech/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.Gagnées en 30 j +339 Score 33,9 Total 341
- 12scott20201225/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.Gagnées en 30 j +322 Score 32,2 Total 322
- 13groundingpi/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.Gagnées en 30 j +285 Score 28,5 Total 291
- 14Forward-Future/folio Folio — a simple, clean, open-source PDF reader for WindowsGagnées en 30 j +263 Score 26,3 Total 263
- 15xristosstarnetgames439-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。Gagnées en 30 j +236 Score 23,6 Total 236
- 16artcraft-android/pdfcraft-android PdfCraft for Android: An Android native open-source PDF reader and editor written in RustGagnées en 30 j +236 Score 23,6 Total 236
- 17baidu/Unlimited-OCR Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.Gagnées en 30 j +3,8 k Score 23,3 Total 30,3 k
- 18sobranie2406/modureader An open-source, cross-platform ebook and PDF reader.Gagnées en 30 j +218 Score 21,8 Total 243
- 19ss062353-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…Gagnées en 30 j +202 Score 20,2 Total 202
- 20cdcailf/cjkfold Fold look-alike CJK glyphs (Kangxi radicals, CJK radical supplements) so text extracted from PDFs matches again.Gagnées en 30 j +195 Score 19,5 Total 195
- 21YOLOW92/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.Gagnées en 30 j +185 Score 18,5 Total 185
- 22virgiliojr94/book-to-skill Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.Gagnées en 30 j +3,3 k Score 18,1 Total 36,7 k
- 23B0yko/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.Gagnées en 30 j +173 Score 17,3 Total 214
- 24rollroyces/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.Gagnées en 30 j +182 Score 17,0 Total 297
- 25AGIHunt/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。Gagnées en 30 j +169 Score 16,9 Total 210
- 26oleost/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.Gagnées en 30 j +167 Score 16,7 Total 188
- 27mg-chao/snow-apps Snow Apps repository, providing source code for Snow Shot and Snow Image Viewer.Gagnées en 30 j +1,2 k Score 16,1 Total 6,6 k
- 28stockedge/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Gagnées en 30 j +160 Score 16,0 Total 160
- 29Tencent/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.Gagnées en 30 j +250 Score 15,5 Total 511
- 30nobell001/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Gagnées en 30 j +141 Score 14,1 Total 141
- 31microsoft/markitdown Python tool for converting files and office documents to Markdown.Gagnées en 30 j +5,9 k Score 13,6 Total 193 k
- 32salikhussain71-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.Gagnées en 30 j +126 Score 12,6 Total 129
- 33fanyuantaier/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Gagnées en 30 j +234 Score 12,3 Total 594
- 34PDFCraftTool/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.Gagnées en 30 j +1,1 k Score 12,0 Total 9,7 k
- 35guaguastandup/zotero-pdf2zh PDF2zh for Zotero | Zotero PDF中文翻译插件Gagnées en 30 j +992 Score 11,8 Total 8 k
- 36chrisryugj/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 diffGagnées en 30 j +562 Score 11,7 Total 2,9 k
- 37lona-cn/vision-simple a lightweight C++ cross-platform vision inference library,support YOLOv10/v11/v26、PaddleOCR,using ONNXRuntime with multiple exectuion providersGagnées en 30 j +118 Score 11,5 Total 223
- 38strugglesky/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。Gagnées en 30 j +115 Score 11,5 Total 115
- 39jev-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。Gagnées en 30 j +971 Score 11,4 Total 8,2 k
- 401003129155/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。Gagnées en 30 j +203 Score 10,8 Total 554
- 412430816465/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。Gagnées en 30 j +108 Score 10,8 Total 108
- 42midagedev/mwoyeo Live, in-place screen translation for macOS — a lens that rewrites the text under it in your language, on-device.Gagnées en 30 j +108 Score 10,8 Total 108
- 43groundingpi/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.Gagnées en 30 j +106 Score 10,6 Total 109
- 44liustack/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)。Gagnées en 30 j +655 Score 10,3 Total 4,7 k
- 45happycola233/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。Gagnées en 30 j +842 Score 10,2 Total 7,6 k
- 46Dai0-2/margino Margino — a browser-native research workspace for Chrome. Read, annotate, ask, remember, and organize papers.Gagnées en 30 j +96 Score 9,6 Total 96
- 47Lechoung-J/reelpack-alpha Reelpack — 给 AI 的视频理解引擎 / The Video-Understanding Engine for AI · License: FSL-1.1-MITGagnées en 30 j +96 Score 9,6 Total 96
- 48motalim-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.Gagnées en 30 j +88 Score 8,8 Total 88
- 49gmi-software/react-native-better-pdf Native, virtualized PDF viewer for React Native, built on Nitro ViewsGagnées en 30 j +87 Score 8,7 Total 88
- 50exuupery/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.Gagnées en 30 j +83 Score 8,3 Total 84
Émergents en PDF & OCR Semaines passées : 26 oct.19 oct.