#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 (+1,938) and Xiaomi-OCR-0 (+596). The 113 ranked repos gained 18,991 stars, 15% more than the week before.
Updated Nov 2, 09:42 UTC · ranked every hour from GitHub’s daily star counts
Updated 11 min ago
This week’s ranking
- 1OpenBMB/MiniCPM-OCR Fast, accurate OCR with correctness assessment.Gained in 7 d +754 Score 75.4 Total 754
- 2SoMarkAI/OXR An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.Gained in 7 d +1.9k Score 62.7 Total 2.9k
- 3xiaomi-research/Xiaomi-OCR-0 Xiaomi-OCR-0Gained in 7 d +596 Score 56.3 Total 708
- 4yjid/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.Gained in 7 d +497 Score 49.7 Total 497
- 5IceWhaleTech/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.Gained in 7 d +327 Score 32.7 Total 329
- 6scott20201225/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.Gained in 7 d +271 Score 27.1 Total 322
- 7Forward-Future/folio Folio — a simple, clean, open-source PDF reader for WindowsGained in 7 d +263 Score 26.3 Total 263
- 8datalab-to/indra 1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracyGained in 7 d +459 Score 13.6 Total 1.6k
- 9strugglesky/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。Gained in 7 d +111 Score 11.1 Total 115
- 10xristosstarnetgames439-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。Gained in 7 d +117 Score 10.7 Total 236
- 11baidu/Unlimited-OCR Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.Gained in 7 d +1.8k Score 10.4 Total 30.3k
- 12YOLOW92/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.Gained in 7 d +92 Score 9.2 Total 184
- 13storytold/pdfcraft PdfCraft: An open-source PDF reader and editor written by scratch in pure RustGained in 7 d +1.2k Score 8.8 Total 19.1k
- 14groundingpi/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.Gained in 7 d +98 Score 7.1 Total 290
- 15LingCore/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.Gained in 7 d +171 Score 6.8 Total 802
- 16Lechoung-J/reelpack-alpha Reelpack — 给 AI 的视频理解引擎 / The Video-Understanding Engine for AI · License: FSL-1.1-MITGained in 7 d +66 Score 6.6 Total 96
- 17sammyZi/pdf-tools 24 free PDF tools and a document scanner for Android. Kotlin + Jetpack Compose, everything on-device, no ads.Gained in 7 d +61 Score 6.1 Total 61
- 18artcraft-android/pdfcraft-android PdfCraft for Android: An Android native open-source PDF reader and editor written in RustGained in 7 d +68 Score 5.2 Total 236
- 19Cynthia-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OCRGained in 7 d +52 Score 5.2 Total 60
- 20FengZhenfei/carrel Ontology-Augmented Generation for AI agents.Gained in 7 d +110 Score 4.6 Total 681
- 21stockedge/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Gained in 7 d +46 Score 4.3 Total 160
- 22AGIHunt/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。Gained in 7 d +49 Score 3.9 Total 210
- 23SpringHgui/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.Gained in 7 d +36 Score 3.6 Total 44
- 24sgfsd/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.Gained in 7 d +35 Score 3.5 Total 48
- 25KalenHwei/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.Gained in 7 d +35 Score 3.5 Total 45
- 26liustack/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)。Gained in 7 d +233 Score 3.5 Total 4.7k
- 27cynicalight/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.Gained in 7 d +58 Score 3.3 Total 371
- 28mg-chao/snow-apps Snow Apps repository, providing source code for Snow Shot and Snow Image Viewer.Gained in 7 d +247 Score 3.1 Total 6.6k
- 29virgiliojr94/book-to-skill Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.Gained in 7 d +587 Score 3.1 Total 36.7k
- 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Gained in 7 d +31 Score 3.0 Total 140
- 31microsoft/markitdown Python tool for converting files and office documents to Markdown.Gained in 7 d +1.2k Score 2.8 Total 193k
- 32valkia/aramgg_client Windows companion for League of Legends ARAM Mayhem with read-only LCU recommendations, Hextech Augment stats, and in-game OCR overlays.Gained in 7 d +67 Score 2.8 Total 622
- 33oleost/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.Gained in 7 d +34 Score 2.7 Total 188
- 34ere123-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.Gained in 7 d +24 Score 2.4 Total 24
- 35Tencent/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.Gained in 7 d +51 Score 2.4 Total 512
- 36fanyuantaier/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Gained in 7 d +54 Score 2.3 Total 594
- 37datalab-to/lift Extract structured data from documents quickly and accurately.Gained in 7 d +78 Score 2.3 Total 1.3k
- 38guaguastandup/zotero-pdf2zh PDF2zh for Zotero | Zotero PDF中文翻译插件Gained in 7 d +196 Score 2.2 Total 8k
- 39TortoTech/torto Next Generation Ebook ReaderGained in 7 d +22 Score 2.2 Total 57
- 40PDFMathTranslate/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。Gained in 7 d +22 Score 2.2 Total 80
- 41motalim-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.Gained in 7 d +21 Score 2.1 Total 88
- 42paperless-ngx/paperless-ngx A community-supported supercharged document management system: scan, index and archive all your documentsGained in 7 d +450 Score 2.1 Total 47.5k
- 43chrisryugj/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 diffGained in 7 d +108 Score 2.0 Total 2.9k
- 44sobranie2406/modureader An open-source, cross-platform ebook and PDF reader.Gained in 7 d +29 Score 2.0 Total 243
- 45opendatalab/MinerU Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.Gained in 7 d +500 Score 1.7 Total 83k
- 46Stirling-Tools/Stirling-PDF #1 PDF Application on GitHub that lets you edit PDFs on any device anywhereGained in 7 d +526 Score 1.7 Total 95.5k
- 47docling-project/docling Get your documents ready for gen AIGained in 7 d +396 Score 1.5 Total 70k
- 48happycola233/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。Gained in 7 d +129 Score 1.5 Total 7.6k
- 49SteveTheKiller/KillerPDF Free and open-source PDF editor for Windows with a built-in PDF 2.0 engine. View, annotate, OCR, merge, split, crop, rotate, compare, edit text, draw, sign, fill forms, print, flatten, and open password-protected PDFs without a subscription.Gained in 7 d +92 Score 1.4 Total 4.3k
- 50PaddlePaddle/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.Gained in 7 d +421 Score 1.4 Total 92.1k
- 51flyfish-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.Gained in 7 d +71 Score 1.4 Total 2.7k
- 52LaoFeng-mouse/flyingmouse-format 飞鼠格式 FlyingMouse Format - Windows 免费文件格式转换工具(离线可用,内置 FFmpeg/LibreOffice/Poppler/Tesseract)。图片/文档/表格/PPT/PDF/音视频/WPS 格式互转 + OCR + 批量转换;音频仅支持普通格式。作者:牢蜂(LaoFeng)|仅供个人免费使用,禁止商业售卖/转卖/套壳Gained in 7 d +111 Score 1.3 Total 7k
- 53yfedoseev/pdf_oxide The fastest PDF library for Python and Rust. Text extraction, image extraction, markdown conversion, PDF creation & editing. 0.8ms mean, 5× faster than industry leaders, 100% pass rate on 3,830 PDFs. MIT/Apache-2.0.Gained in 7 d +43 Score 1.3 Total 1.2k
- 54docusealco/docuseal Open source DocuSign alternative. Create, fill, and sign digital documents ✍️Gained in 7 d +175 Score 1.3 Total 19k
- 55ooboqoo/shiping 识屏 Shiping:截屏 + AI,看懂屏幕上的任何内容。代码、报错、题目、图表、外文资料,按快捷键截一下就有解答;常驻后台,随时框选识别。对话模式实时听懂问题、给出回答要点。可用作面试助手、考试助手、刷题助手。Gained in 7 d +42 Score 1.3 Total 1.1k
- 56jiuwanzi-hui/Screenshot SnapCut(简截)——轻巧但不将就的 Windows 和 macOS 截图工作台:框选截图、长截图、区域录屏、钉图取色、标注、OCR 与翻译一体化。支持保留右键菜单和悬浮提示,数据永久留在本机。Gained in 7 d +21 Score 1.2 Total 309
- 57firecrawl/anydoc Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.Gained in 7 d +185 Score 1.2 Total 23.3k
- 58jev-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。Gained in 7 d +109 Score 1.2 Total 8.2k
- 59PDFMathTranslate/PDFMathTranslate [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译,支持 Google/DeepL/Ollama/OpenAI 等服务,提供 CLI/GUI/MCP/Docker/ZoteroGained in 7 d +231 Score 1.2 Total 38.1k
- 60tw93/Kami 👩🚒 Good content deserves good paper. Layout rules and templates that let AI agents export PDF, PNG and editable PowerPoint.Gained in 7 d +126 Score 1.1 Total 12.2k
- 61Zipstack/unstract LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline WorkflowsGained in 7 d +97 Score 1.1 Total 7.4k
- 62fschutt/printpdf Rust / WASM library for reading, writing and rendering PDFGained in 7 d +38 Score 1.1 Total 1.2k
- 63OpenSenseNova/SenseNova-Skills Modular SenseNova skills for building AI-powered office assistants and productivity workflowsGained in 7 d +85 Score 1.1 Total 6k
- 64ciromattia/kcc KCC (a.k.a. Kindle Comic Converter) is a comic and manga converter for ebook readers.Gained in 7 d +81 Score 1.1 Total 6k
- 65RapidAI/RapidOCR 📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.Gained in 7 d +93 Score 1.0 Total 8.4k
- 66STranslate/STranslate A ready-to-go translation ocr tool developed with WPF/WPF 开发的一款即用即走的翻译、OCR工具Gained in 7 d +93 Score 1.0 Total 8.5k
- 67hgmzhn/manga-translator-ui 基于manga-image-translator 实现的开源漫画AI翻译桌面工具。支持日、韩、英文漫画自动处理,集成OpenAl、Gemini等多翻译引擎;实现OCR文字检测、原文擦除、AI翻译、图像修复、译文排版完整链路,自带可视化编辑器,支持自定义文本样式,一键部署开箱即用。Gained in 7 d +55 Score 1.0 Total 3.2k
- 68mokshablr/gander Take a gander at any file. Offline, zero-permission Android viewer for PDF, Word, Excel, PowerPoint, ODT, RTF, ZIP, STL, photos, video, audio, Markdown and code.Gained in 7 d +32 Score 0.9 Total 1.4k
- 69OpenAEC-Foundation/open-pdf-studio An open source PDF viewer/editor with it's own blazing fast rust engineGained in 7 d +27 Score 0.9 Total 983
- 70xerrors/Yuxi 可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.Gained in 7 d +74 Score 0.9 Total 7.6k
- 71ShareX/ShareX ShareX is a free and open-source application that enables users to capture or record any area of their screen with a single keystroke. It also supports uploading images, text, and various file types to a wide range of destinations.Gained in 7 d +168 Score 0.8 Total 40.6k
- 72hiroi-sora/Umi-OCR OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片,PDF文档识别,排除水印/页眉页脚,扫描/生成二维码。内置多国语言库。Gained in 7 d +177 Score 0.8 Total 48.4k
- 73pynicolas/FairScan An Android app to scan your documents — simple and respectfulGained in 7 d +25 Score 0.8 Total 1k
- 74PDFCraftTool/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.Gained in 7 d +78 Score 0.8 Total 9.7k
- 75HIllya51/LunaTranslator 视觉小说翻译器 / Visual Novel TranslatorGained in 7 d +92 Score 0.8 Total 14k
- 76opendataloader-project/opendataloader-pdf PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.Gained in 7 d +132 Score 0.8 Total 30.1k
- 77umlx5h/LLPlayer The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!Gained in 7 d +50 Score 0.8 Total 4.5k
- 78tisfeng/Easydict 一个简洁优雅的词典翻译 macOS App。开箱即用,支持离线 OCR 识别,支持有道词典,🍎 苹果系统词典,🍎 苹果系统翻译,OpenAI,Gemini,DeepL,Google,Bing,腾讯,百度,阿里,小牛,彩云和火山翻译。A concise and elegant Dictionary and Translator macOS App for looking up words and translating text.Gained in 7 d +88 Score 0.7 Total 15.2k
- 79FB208/OpenBidKit_Yibiao 开箱即用的AI标书编写工具,标书AI生成工具,投标工具箱、知识库、标书查重、废标项检查,完全开源免费,欢迎使用Gained in 7 d +39 Score 0.7 Total 3.3k
- 80xberg-io/xberg The fast, precise document-intelligence engine for every language: text, tables and metadata from 100+ formats, with OCR, transcription and code intelligence.Gained in 7 d +66 Score 0.7 Total 9.5k
- 81alam00000/bentopdf The Privacy First PDF ToolkitGained in 7 d +85 Score 0.7 Total 16.2k
- 82datalab-to/chandra OCR model that handles complex tables, forms, handwriting with full layout.Gained in 7 d +75 Score 0.7 Total 12.7k
- 83shcherbak-ai/contextgem Extract structured data and insights from documents using LLMs and decision modelsGained in 7 d +30 Score 0.7 Total 2k
- 84ucbepic/docetl A system for agentic LLM-powered data processing and ETLGained in 7 d +43 Score 0.7 Total 4.2k
- 85dominostars/playtranslate Real-time translation and language learning Android app for games, visual novels, manga, and any other screen text. 屏幕翻译 游戏翻译Gained in 7 d +23 Score 0.6 Total 1.3k
- 86pdfme/pdfme Open-source PDF generation library built with TypeScript and React. Features a WYSIWYG template designer, PDF viewer, and powerful generation capabilities. Create custom PDFs effortlessly in both browser and Node.js environments.Gained in 7 d +44 Score 0.6 Total 5k
- 87CVHub520/X-AnyLabeling X-AnyLabeling: A lightweight, efficient, and unified cross-platform desktop application for annotating text, image, video, point cloud and multimodal data, combining versatile built-in tools with state-of-the-art AI models and flexible multi-format export.Gained in 7 d +65 Score 0.6 Total 10.9k
- 88datalab-to/marker Convert PDF to markdown + JSON quickly with high accuracyGained in 7 d +114 Score 0.6 Total 40.7k
- 89cyanfish/naps2 Scan documents to PDF and more, as simply as possible.Gained in 7 d +38 Score 0.6 Total 4.7k
- 90C4illin/ConvertX 💾 Self-hosted online file converter. Supports 1000+ formats ⚙️Gained in 7 d +76 Score 0.5 Total 19.3k
Emerging in PDF & OCR Past weeks: Oct 26Oct 19