This is your work, valued
CacheWebView. Custom implement Android WebView cache, offline website, let cahe config more simple and flexible
★ 2kRetrofitCache. RetrofitCache让retrofit2+okhttp3+rxjava配置缓存如此简单。通过注解配置,可以针对每一个接口灵活配置缓存策略;同时让每一个接口方便支持数据模拟,可以代码减小侵入性,模拟数据可以从内存,Assets,url轻松获取。
★ 676EasyIncrementalUpdate. Android差分补丁库,通过native层合并APK,实现增量更新升级,让你更新的APK更小。
★ 236Summer. Vertx router with JAX-RS
★ 67quickapp-wechat. 快应用实现的微信Demo
★ 48EasyJSBridge. 让JS在Android/iOS WebView中反调接口统一,调用更容易
★ 43gorpool. Simple Goroutine pool
★ 36stream. Golang stream lib is like Java 8 stream. Only handle slice or array.
★ 9deploy. 通过SSH连接,简单的配置文件,可以配置私钥,可以配置socks5,让部署更简单
★ 7JavaAutoDeployClient. java auto deploy
★ 6doris-stream-loader. Apache Doris Stream Loader Golang API
★ 5gank-uni-app. gank-uni-app 通过uni-app框架,调用gank.io接口写的干货集中营Demo,通过HBuilderX将项目打包为APP,包括iOS、Android、H5、微信小程序,支付宝小程序,百度小程序、头条小程序
★ 5gffmpeg. golang ffmpeg wrapper
★ 5VideoUtil. 给视频添加关键帧工具
★ 5gosocket. Simple Golang server socket long connection skeleton
★ 5weixin-service. Golang微信,小程序后台接口
★ 5ScrollViewSlipping. android ScrollViewSlipping
★ 4url-to-pdf-api-docker. url-to-pdf-api docker build
★ 3goutils. A set of tools that keep Golang sweet.
★ 3caddy-build. caddy build with some plugins
★ 2jpinyin. JPinyin是一个汉字转拼音的Java开源类库
★ 2nw-windows-easy-package. node-webkit windows easy package
★ 2PopList. Android poplist
★ 2Axis1WebService. Axis1 WebService 例子,通过wsdl文件生成服务器端代码并部署
★ 1ImageDeskew. ImageDeskew
★ 1android-apk-decompile. Android decompile tools for mac(安卓apk反编译工具,一键反编译AndroidMainfest.xml layout res等资源以及class文件)
★ 1timer-message. Simple windows timer to show message box.
★ 1android-architecture. A collection of samples to discuss and showcase different architectural tools and patterns for Android apps.
★ 1Roadmap. Go
★ 1go-commons. go-commons
★ 1paysdk. Go
★ 1url-to-pdf-api. Web page PDF/PNG rendering done right. Self-hosted service for rendering receipts, invoices, or any content.
★ 1DataUpdater. Golang remote data update with timer lib. You can update config auto.
★ 1aes-everywhere. Aes Everywhere - Cross Language AES 256 Encryption Library (Bash, Powershell, C#, Dart, GoLang, Java, JavaScript, Lua, PHP, Python, Ruby, Swift)
★ 1encrypt-decrypt. Java、Go、Python、NodeJS、PHP、JavaScript AES/CBC/PKCS7Padding 加解密
★ 1vue-installer. vue component installer from github
★ 1Axis1WebServiceClient. Axis1 WebService 客户端 例子,通过wsdl文件生成客户端代码并调用
★ 1Words. Words is for sentence util kit.
★ 1docker-playwright-python. Playwright Python Docker image
★ 1xlsx2db. load xlsx file to db
★ 1deployx. Node deploy cli utils
★ 1vue-admin-frame. Simple vue admin frame demo, use vue2.0, element-ui
★ 1JieCaoVideoPlayer. Android VideoPlayer MediaPlayer VideoView MediaView Float View And Fullscreen
★ 1ratelimiter. ratelimiter is wrapper token-bucket and count-limit by golang
★ 1wkvideoplayer. Java
★ 1minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM!Train a 64M-parameter LLM from scratch in just 2h!
★ 53kpi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
★ 70knuwa-skill. 你想蒸馏的下一个员工,何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
★ 28kegui. egui: an easy-to-use immediate mode GUI in Rust that runs on both web and native
★ 30kavtr-1. AVTR-1: Avatars that listen back
★ 364modly. Desktop app to generate 3D models from images using local AI — runs entirely on your GPU
★ 4.3kX-Dub. Try X-Dub to sync any character in a video with any audio you like | Official repository for "From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping"
★ 214AudioX-Turbo. 🚀 Fastest Anything-to-Audio Gen for conditioned sound and music creation.
★ 216SCAIL-2. Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning
★ 926egui_code_editor. egui Code Editor widget with numbered lines and syntax highlighting..
★ 134gorest-2d-animation-spritesheet-generator. Codex-assisted local 2D animation spritesheet generator and scene compositing workspace.
★ 1.1kSysMocap. A real-time motion capture system for 3D virtual character animating.
★ 3.2kGR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC
★ 2.9kIterative-Contextual-Refinements. Using BFS & DFS like techniques over LLMs for iteratively exploring the solution search space at scale.
★ 725MiMo-Code. MiMo Code: Where Models and Agents Co-Evolve
★ 12kLipForcing. Python
★ 86FlashVGGT. Accelerate VGGT with efficient desciptor-based global attention
★ 96MeloTTS.cpp. A lightweight pure C++ Text-to-Speech (TTS) pipeline with OpenVINO, supporting multiple languages.
★ 108psmux. Tmux on Windows Powershell - tmux for PowerShell, Windows Terminal, cmd.exe. Includes psmux, pmux, and tmux commands. This is native Powershell Tmux designed for Windows in Rust 🦀
★ 2.9konnxruntime_purego. 基于 purego 直接绑定并调用 onnxruntime 原生库接口,无需依赖 CGO 编译环境,即可实现 ONNX 模型的加载与推理计算
★ 19xiaozhi-assets-generator. JavaScript
★ 136carbon. The home of Carbon Genomic Foundation Model 🧬
★ 199xiaozhi-esp32-server-golang. golang版本的小智后端服务,支持websocket和mqtt+udp协议,支持声纹识别/声音克隆/知识库/mcp远程调用/主动音频下发/openclaw等功能
★ 369xiaozhi-server-go. Go
★ 457flash-attention. Fast and memory-efficient exact attention
★ 24kKittenTTS. State-of-the-art TTS model under 25MB 😻
★ 15kpocket-tts. A TTS that fits in your CPU (and pocket)
★ 7.3ksupertonic. Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
★ 13kmammothmoda. Python
★ 328jichangtuijian. 梯子机场推荐
★ 1.8ktools-config. Shell
★ 16ruflo. 🌊 The leading agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
★ 64kFlClash. A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
★ 45kopen-codesign. Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama). BYOK, local-first, MIT.
★ 7.2kSprite-Pipeline. 2D Sprite Sheet Creation Pipeline
★ 568evo2. Genome modeling and design across all domains of life
★ 4kagent-framework. A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
★ 12kCyberVerse. Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
★ 1.4kVRAG. Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.
★ 961codesurf. context IDE
★ 285rhubarb-lip-sync. Rhubarb Lip Sync is a command-line tool that automatically creates 2D mouth animation from voice recordings. You can use it for characters in computer games, in animated cartoons, or in any other project that requires animating mouths based on existing recordings.
★ 2.5kLTX-Desktop. An open-source desktop app for generating videos with LTX models
★ 1.8kawesome-agent-skills. A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
★ 28kgsd-2. A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
★ 7.7khyperframes. Write HTML. Render video. Built for agents.
★ 34kPixelle-Video. 🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine
★ 25kSentiAvatar. Python
★ 323SymSpell. SymSpell: 1 million times faster spelling correction & fuzzy search through Symmetric Delete spelling correction algorithm
★ 3.5kmastra. Mastra is the modern TypeScript framework for AI-powered applications and agents.
★ 26kvoid. TypeScript
★ 29ktheia. Eclipse Theia is a cloud & desktop IDE framework implemented in TypeScript.
★ 22kvscode-extension. Flexpilot - Open-Source, Native and a True GitHub Copilot Alternative for VS Code
★ 821Async. IDE, A native-feeling AI coding workspace that blends chat, planning, agent execution, and project navigation into a unified desktop experience.
★ 481flexpilot-ide. Flexpilot IDE - Open-Source AI Native IDE
★ 2.6kdeepxiv_sdk. Talk to research papers like talking to authors - Python package with AI agent for arXiv papers
★ 736SoulX-LiveAct. Official inference code for SoulX-LiveAct: Towards Hour-Scale Real-Time Human Animation with Neighbor Forcing and ConvKV Memory
★ 1.1kHyperAgents. Self-referential self-improving agents that can optimize for any computable task
★ 2.6kOpenHarness. "OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
★ 15kPageIndex. 📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
★ 34kAwesome-Document-Image-Rectification. A comprehensive list of awesome document image rectification papers.
★ 555DocScanner. The official repo for “DocScanner: Robust Document Image Rectification with Progressive Learning”, IJCV, 2025.
★ 334DRCCBI. Python
★ 34deskew. Library used to deskew a scanned document
★ 521DocuNet. [IJCAI 2021] Document-level Relation Extraction as Semantic Segmentation
★ 157eruda. Console for mobile browsers
★ 21kopendev. Open-Source Coding Agent in the terminal
★ 745diff-match-patch. Diff Match Patch is a high-performance library in multiple languages that manipulates plain text.
★ 8.1kMemento-Skills. Memento-Skills: Let Agents Design Agents
★ 1.5kopenclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
★ 383kQwenPaw. Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
★ 22kClawTeam. "ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)
★ 5.4kopenai-agents-python. A lightweight, powerful framework for multi-agent workflows
★ 28kCLI-Anything. "CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
★ 45kai-town. A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.
★ 10kAgentTeams. An open-source Collaborative Multi-Agent OS for transparent, human-in-the-loop task coordination via Matrix rooms.
★ 5kantigravity-proxy. 🚀 Transparent proxy injector for Antigravity. Force SOCKS5/HTTP proxy without TUN mode on Windows. | 专为 Antigravity 打造的免 TUN 强制代理工具,支持 DLL 注入与进程流量劫持。
★ 3.4kWindows-MCP. MCP Server for Computer Use in Windows
★ 6.4kSpacetimeDB. Development at the speed of light
★ 25ktiny_container. Click-to-run debian 13 with desktop environment on android!
★ 3.6kDeepCode. "DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
★ 16kstitch-skills. A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents such as Antigravity, Gemini CLI, Claude Code, Cursor.
★ 6.9kone-person-unicorn-book. The One-Person Unicorn — A Possible Form of the One-Person Company When Agents Can Work Independently |《一人独角兽》—— 当智能体可以独立工作时,一人公司的一种可能解
★ 159ai-money-maker-handbook. ai副业赚钱大集合,教你如何利用ai做一些副业项目,赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English version for more insights.
★ 2.9kaimoneyhunter. ai副业赚钱大集合,教你如何利用ai做一些副业项目,赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English version for more insights.
★ 18kakshare. AKShare is an elegant and simple financial data interface library for Python, built for human beings! 开源财经数据接口库
★ 21kTradingAgents-CN. 基于多智能体LLM的中文金融交易框架 - TradingAgents中文增强版
★ 30kmathlive. Web components for math display and input
★ 2.1kmemU. Personal memory for agents - fast memory retrieval, self-evolving skills, and lower cost.
★ 14kUniRig. [SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
★ 1.6kRigAnything. RigAnything: Template‑Free Autoregressive Rigging for Diverse 3D Assets (SIGGRAPH TOG 2025)
★ 150nanoclaw. A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
★ 30knanobot. Lightweight, open-source AI agent for your tools, chats, and workflows.
★ 45kAnimatedDrawings. Code to accompany "A Method for Animating Children's Drawings of the Human Figure"
★ 13kvibe-kanban. Get 10X more out of Claude Code, Codex or any coding agent
★ 27ksuperpowers. An agentic skills framework & software development methodology that works.
★ 252kOpenSpec. Spec-driven development (SDD) for AI coding assistants.
★ 60kchrome-devtools-mcp. Chrome DevTools for coding agents
★ 47kui-ux-pro-max-skill. An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms
★ 104kdeepagents. The batteries-included agent harness.
★ 26kfaster-whisper. Faster Whisper transcription with CTranslate2
★ 24kAI-Guide-and-Demos-zh_CN. 这是一份入门AI/LLM大模型的逐步指南,包含教程和演示代码,带你从API走进本地大模型部署和微调,代码文件会提供Kaggle或Colab在线版本,即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡,你可以尝试在里面实验一些有意思的AI脚本。同时,包含李宏毅 (HUNG-YI LEE)2024生成式人工智能导论课程的完整中文镜像作业。
★ 4.3kdinov3-samples. dinov3例子
★ 101dinov3-train. DINOv3训练示例
★ 169pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
★ 37klightly-train. All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.
★ 1.6kMedDINOv3. MedDINOv3: How to adapt vision foundation models for medical image segmentation?
★ 220dinov3. Reference PyTorch implementation and models for DINOv3
★ 11kTurboDiffusion. TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
★ 3.6kReMe. ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
★ 3.2kGenieX. Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code
★ 8.2kPersonaLive. [CVPR 2026] PersonaLive! : Expressive Portrait Image Animation for Live Streaming
★ 3.4kLLaDA2.X. LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.
★ 442editor. Umo Editor is an open-source document editor based on Vue3 and Tiptap3, providing an online editing experience similar to Microsoft Word.
★ 1.5kOpen-AutoGLM. An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
★ 26kopen-source-games. A list of open source games.
★ 13kAgent-S. Agent S: an open agentic framework that uses computers like a human
★ 12kFoundry-Local. C++
★ 2.4kLyra. Lyra v2.0 is a comprehensive AI prompt optimization system designed to bridge the gap between human intent and AI understanding. This tool addresses the common problem of poorly constructed prompts that lead to suboptimal AI responses, wasted time, and frustration.
★ 12MemMachine. Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
★ 3.3kMemori. Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
★ 16kdocument. Perform common file preview and editing via the web.
★ 1.8kdocling. Get your documents ready for gen AI
★ 63kvue-office. 支持word(.docx)、excel(.xlsx,.xls)、pdf、pptx等各类型office文件预览的vue组件集合,提供一站式office文件预览方案,支持vue2和3,也支持React等非Vue框架。Web-based pdf, excel, word, pptx preview library
★ 5.6kchandra. OCR model that handles complex tables, forms, handwriting with full layout.
★ 11kultralytics. Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
★ 59kclaude-code-router. Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
★ 36kPVE-Tools-9. 面向 Proxmox VE 9.x 的一键运维脚本,覆盖 VM 生命周期运维、宿主机网络 / 防火墙 / IPv6、GPU / PCI 直通、系统维护与第三方生态集成。
★ 2kktransformers. A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
★ 17ktango. A code driven low-code builder, develop low-code app on your codebase.
★ 3.1kdeepseek. DeepSeek 官网入口、下载及使用教程~ | DeepSeek 最新使用指南~【2025年10月更新】 轻松使用 DeepSeek 网页版,快速稳定、不卡顿,支持 DeepSeek R1 满血版 以及 ChatGPT o1、o3 大模型 本指南提供最全面的 DeepSeek 使用指南,包含 DeepSeek 官网入口、DeepSeek 网页版、deepseek 下载、DeepSeek 平替网站、,助您顺畅使用 DeepSeek~
★ 4HRM. Hierarchical Reasoning Model Official Release
★ 13kpydantic-ai. AI Agent Framework, the Pydantic way
★ 18kengine. A typescript interactive engine, support 2D, 3D, animation, physics, built on WebGL and glTF.
★ 5.8kphaser-box2d. A high-performance, industry-standard 2D physics engine built on Box2D v3, delivering incredibly realistic and engaging web game experiences.
★ 156code-run. 一个代码在线编辑预览工具,类似codepen、jsbin、jsfiddle等。
★ 615jsxgraph. JSXGraph is a cross-browser library for interactive geometry, function plotting, charting, and data visualization in a web browser.
★ 1.4kVirtualBuddy. Virtualize macOS 12 and later on Apple Silicon, VirtualBuddy is a virtual machine GUI for macOS M1, M2, M3, M4
★ 8.3kbananas. Bananas🍌, Cross-Platform screen 🖥️ sharing 📡 made simple ⚡.
★ 6.2kunifolm-world-model-action. Python
★ 1.1keveryone-can-use-english. 人人都能用英语
★ 35kHuMo. HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
★ 1.3kawesome-ai-agents. A list of AI autonomous agents
★ 29kChinaTextbook. 所有小初高、大学PDF教材。
★ 76kmarkitdown. Python tool for converting files and office documents to Markdown.
★ 165ksiyuan. A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.
★ 45kpresenton. Open-Source AI Presentation Generator and API (Gamma, Canva, Beautiful AI, Decktopus, Presentations AI Alternative)
★ 9ktalking-head-anime-4-demo. Demo Programs for the "Talking Head(?) Anime from a Single Image 4: Improved Models and Its Distillation" Project
★ 341Mate-Engine. A free Desktop Mate alternative with a lightweight interface and custom VRM support, though with more features.
★ 3.4ksqler. write APIs using direct SQL queries with no hassle, let's rethink about SQL
★ 2.1kDBAPI. Build rest API with SQL in one minute
★ 798OxyGent. [ACL 2026] OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction https://arxiv.org/abs/2604.25602
★ 2kUI-TARS-desktop. The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
★ 38kBriLLM0.5. Python
★ 322Bella. Bella is best
★ 6.4kdoctr. docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.
★ 6.2kunsloth. Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
★ 68kms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
★ 15kRecorder. html5 js 录音 mp3 wav ogg webm amr g711a g711u 格式,支持pc和Android、iOS部分Web浏览器、Hybrid App(提供Android iOS App源码)、微信,提供ASR语音识别转文字 H5版语音通话聊天示例 DTMF编码解码
★ 5.6kMarior. [ACM MM 2022] Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild
★ 26Doc-Image-Tool. 文档图像处理工具(Document image processing tool),包括漂白 / 文字方向矫正 / 清晰增强 / 笔记去噪美化 / 去阴影 / 扭曲矫正 / 切边增强(DocBleach / TextOrientationCorrection / DocSharpening / HandwritingDenoisingBeautifying / DocShadowRemoval / document_image_dewarping / DocTrimmingEnhancement)。
★ 134RapidUnDistort. 修正文档扭曲/模糊/阴影等情况,使用onnx模型简单轻量部署,未来持续跟进最新最好的文档矫正方案和模型,Correct document distortion using a lightweight ONNX model for easy deployment. We will continue to follow and integrate the latest and best document correction solutions and models in the future.
★ 105mkcert. A simple zero-config tool to make locally trusted development certificates with any names you'd like.
★ 59kdots.ocr. Multilingual Document Layout Parsing in a Single Vision-Language Model
★ 9kjoyagent-jdgenie. 开源的端到端产品级通用智能体
★ 12kOCRFlux. OCRFlux is a lightweight yet powerful multimodal toolkit that significantly advances PDF-to-Markdown conversion, excelling in complex layout handling, complicated table parsing and cross-page content merging.
★ 2.5kLiveTalking. Real time interactive streaming digital human
★ 8.4kdocext. An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https://idp-leaderboard.org/)
★ 2kMonkeyOCR. A lightweight LMM-based Document Parsing Model
★ 6.6kvosk-android-demo. Offline speech recognition for Android with Vosk library.
★ 1.1kvosk-api. Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
★ 15kWiaDotNet. A wrapper for WIA scanners
★ 1naps2. Scan documents to PDF and more, as simply as possible.
★ 4.3knaps2-wia. Low-level WIA 2.0/1.0 application library for .NET
★ 22Saraff.Twain.NET. Saraff.Twain.NET is the skillful scanning component which allows you to control work of flatbed scanner, web and digital camera and any other TWAIN device from .NET environment. You can use this library in your programs written in any programming languages compatible with .NET technology.
★ 110PaddleX. All-in-One Development Tool based on PaddlePaddle
★ 6.2kedu-knowlege. 教育各种资料,从幼儿园到小学、中学,涵盖学而思,万维、猿辅导等多个机构,持续增加中
★ 4.2kDocLayout-YOLO. DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
★ 2.2kEasyOCR. Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
★ 30kMontreal-Forced-Aligner. Command line utility for forced alignment using Kaldi
★ 1.8klancedb. Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.
★ 11kopenui. OpenUI let's you describe UI using your imagination, then see it rendered live.
★ 22kFramePack. Lets make video diffusion practical!
★ 17kadk-python. An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
★ 21klangchain-mcp-adapters. LangChain 🔌 MCP
★ 3.6kkonva. Konva.js is an HTML5 Canvas JavaScript framework that extends the 2d context by enabling canvas interactivity for desktop and mobile applications.
★ 15kidraw. A simple JavaScript framework for Drawing on the web.(一个面向Web绘图的JavaScript框架)
★ 1.1kfabric.js. Javascript Canvas Library, SVG-to-Canvas (& canvas-to-SVG) Parser
★ 31klangflow. Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
★ 152kDocumentServer. ONLYOFFICE Docs is a free collaborative online office suite comprising viewers and editors for texts, spreadsheets and presentations, forms and PDF, fully compatible with Office Open XML formats: .docx, .xlsx, .pptx and enabling collaborative editing in real time.
★ 6.7kinspira-ui. Build beautiful website using Vue & Nuxt.
★ 4.7kpdf-craft. PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.
★ 5.9kDocs2KG. Docs2KG: A Human-LLM Collaborative Approach to Unified Knowledge Graph Construction from Heterogeneous Documents
★ 370iii. Effortlessly compose, extend, and observe every service in real-time for the first time ever.
★ 18kai-app-lab. TypeScript
★ 2.4kweaviate. Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
★ 17kdify-plus. Dify-Plus 是 Dify 的企业级增强版,集成了基于 gin-vue-admin 的管理中心,并针对企业场景进行了功能优化。 🚀 Dify-Plus = 管理中心 + Dify 二开 。 特别说明: 本项目为开源社区的二次开发成果,严格遵循 Dify 原项目的版权许可协议,未涉及原项目许可的多租户功能及 logo 等版权信息。如有相关需求,请直接联系 Dify 官方获取授权与支持。
★ 2.2ksurya. OCR, layout analysis, reading order, table recognition in 90+ languages
★ 21kMinerU. Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
★ 74klayoutreader. A Faster LayoutReader Model based on LayoutLMv3, Sort OCR bboxes to reading order.
★ 322PDFMathTranslate. [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/Zotero
★ 36k