Top 100 GUI Agent Repositories
Ranking
| Ranking | Project Name | Stars | Forks | Language | Open Issues | Description | Last Commit |
|---|---|---|---|---|---|---|---|
| 1 | JavaGuide | 155,812 | 46,138 | JavaScript | 61 | Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发 | 2026-05-21 |
| 2 | Prompt-Engineering-Guide | 74,841 | 8,105 | MDX | 175 | 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents. | 2026-03-11 |
| 3 | OmniParser | 24,790 | 2,172 | Jupyter Notebook | 173 | A simple screen parsing tool towards pure vision based GUI agent | 2026-04-13 |
| 4 | opcode | 21,915 | 1,693 | TypeScript | 268 | A powerful GUI app and Toolkit for Claude Code - Create custom agents, manage interactive Claude Code sessions, run secure background agents, and more. | 2025-10-16 |
| 5 | page-agent | 18,003 | 1,530 | TypeScript | 32 | JavaScript in-page GUI agent. Control web interfaces with natural language. | 2026-05-11 |
| 6 | ChuanhuChatGPT | 15,332 | 2,239 | Python | 122 | GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI. | 2026-04-30 |
| 7 | ai-guide | 14,294 | 1,622 | JavaScript | 6 | 程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skills / RAG / MCP / A2A）、AI 编程教程（Harness Engineering）、AI 工具用法（Cursor /... | 2026-04-30 |
| 8 | guizang-ppt-skill | 11,014 | 867 | HTML | 6 | AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime. | 2026-05-19 |
| 9 | UI-TARS | 10,686 | 800 | Python | 40 | Pioneering Automated GUI Interaction with Native Agents | 2026-01-27 |
| 10 | UFO | 8,713 | 1,022 | Python | 40 | UFO³: Weaving the Digital Agent Galaxy | 2026-05-15 |
| 11 | MobileAgent | 8,697 | 878 | Python | 183 | Mobile-Agent: The Powerful GUI Agent Family | 2026-05-14 |
| 12 | CodePilot | 5,767 | 619 | TypeScript | 357 | A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js. | 2026-05-11 |
| 13 | AgentGuide | 5,030 | 502 | HTML | 80 | https://adongwanai.github.io/AgentGuide | AI Agent开发指南 | LangGraph实战 | 高级RAG | 转行大模型 | 大模型面试 | 算法工程师 | 面试题库 | 强化学习｜数据合成 | 2026-05-18 |
| 14 | claude-code-ultimate-guide | 4,444 | 587 | TypeScript | 3 | A tremendous feat of documentation, this guide covers Claude Code from beginner to power user, with production-ready templates for Claude Code features, guides on agentic workflows, and a lot of great... | 2026-05-21 |
| 15 | claude-code-guide | 4,155 | 409 | - | 2 | Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user! | 2026-05-22 |
| 16 | china-dictatorship | 3,000 | 289 | HTML | 848 | 反中共政治宣传库。Anti Chinese government propaganda. 住在中国真名用户的网友请别给星星，不然你要被警察请喝茶。常见问答集，新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件邓家贵低端人口西藏骚乱。Friends who live in China and have real name on ac... | 2026-02-05 |
| 17 | OSWorld | 2,865 | 461 | Python | 147 | [NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments | 2026-05-21 |
| 18 | openclaw-security-practice-guide | 2,834 | 197 | Shell | 3 | This guide is designed for OpenClaw itself (Agent-facing), not as a traditional human-only hardening checklist. | 2026-04-06 |
| 19 | gelab-zero | 2,169 | 193 | Python | 38 | STEP-GUI: The top GUI agent solution in the galaxy. Developed by the StepFun-GELab team and powered by StepFun’s cutting-edge research capabilities. | 2026-05-11 |
| 20 | Mano-P | 2,123 | 191 | - | 19 | Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacB... | 2026-05-09 |
| 21 | computer_use_ootb | 1,942 | 205 | Python | 33 | Out-of-the-box (OOTB) GUI Agent for Windows and macOS | 2025-05-21 |
| 22 | .github | 1,886 | 151 | - | 0 | 这里是GitHub的草场，也是戈戈圈爱好者的交流地，主要讨论动漫、游戏、科技、人文、生活等所有话题，欢迎各位小伙伴们在此讨论趣事。This is GitHub grassland, and the community place for Gege circle lovers, mainly discusses anime, games, technology, lifing and other t... | 2025-10-04 |
| 23 | ShowUI | 1,839 | 139 | Python | 15 | [CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use. | 2026-04-24 |
| 24 | MobiAgent | 1,827 | 226 | Python | 7 | The Intelligent GUI Agent for Mobile Phones | 2026-05-21 |
| 25 | MAI-UI | 1,808 | 176 | Jupyter Notebook | 31 | MAI-UI: Real-World Centric Foundation GUI Agents ranging from 2B to 235B | 2026-04-20 |
| 26 | OpenOmniBot | 1,457 | 45 | Kotlin | 10 | Your on-device AI assistant, capable of operating terminals and performing a wide range of tasks in the Android world || 你的端侧 AI 助手，她可以操作终端，也可以完成 Android 世界的广泛任务 | 2026-05-22 |
| 27 | AgentCPM-GUI | 1,367 | 130 | Python | 2 | AgentCPM-GUI: An on-device GUI agent for operating Android apps, enhancing reasoning ability with reinforcement fine-tuning for efficient task execution. | 2026-01-11 |
| 28 | pywinassistant | 1,341 | 188 | Python | 10 | The first open-source Artificial Narrow Intelligence generalist agentic framework Computer-Using-Agent that fully operates graphical-user-interfaces (GUIs) by using only natural language. Uses Visuali... | 2025-02-13 |
| 29 | CrewAI-Studio | 1,271 | 308 | Python | 19 | A user-friendly, multi-platform GUI for managing and running CrewAI agents and tasks. Supports Conda and virtual environments, no coding needed. | 2026-03-27 |
| 30 | ClawGUI | 1,265 | 48 | Python | 1 | Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework. | 2026-05-21 |
| 31 | codeg | 1,221 | 133 | TypeScript | 48 | Aggregate and browse AI coding agent sessions (Claude Code, Codex, Gemini CLI, etc.) in one place. Desktop app, self-hosted server, or Docker. | 2026-05-22 |
| 32 | Awesome-GUI-Agent | 1,192 | 72 | - | 4 | 💻 A curated list of papers and resources for multi-modal Graphical User Interface (GUI) agents. | 2025-08-17 |
| 33 | CogAgent | 1,180 | 99 | Python | 28 | An open-sourced end-to-end VLM-based GUI Agent | 2025-04-04 |
| 34 | UI-Venus | 1,006 | 84 | Python | 10 | UI-Venus is a native UI agent designed to perform precise GUI element grounding and effective navigation using only screenshots as input. | 2026-05-11 |
| 35 | ai-agent-interview-guide | 981 | 108 | Python | 2 | AI Agent 面试全攻略：从零到Offer，包含200+面试题、企业级项目(Python/Java/Go)、简历模板、STAR面试稿、哆啦A梦漫画图解 | 2026-04-01 |
| 36 | claude-code-design-guide | 812 | 273 | JavaScript | 0 | From Early Internet Design Patterns to AI Agent Implementation — A Deep Dive into Claude Code for Developers | 2026-04-15 |
| 37 | GUI-Agents-Paper-List | 785 | 41 | TypeScript | 1 | Awesome GUI Agent Paper List | 2026-05-12 |
| 38 | OpenCUA | 766 | 99 | Python | 14 | [NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents | 2026-02-04 |
| 39 | agentcloud | 683 | 141 | TypeScript | 81 | Agent Cloud is like having your own GPT builder with a bunch extra goodies. The GUI features 1) RAG pipeline which can natively embed 260+ datasources 2) Create Conversational apps (like GPTs) 3) Crea... | 2025-07-21 |
| 40 | Practical-Guide-to-Context-Engineering | 658 | 55 | - | 0 | 大模型应用开发的方向，上下文工程是设计原则，Agent Harness 是构建目标，本项目的目标，是为开发者和研究者提供一份大模型应用开发的骨架思路 | 2026-05-06 |
| 41 | AppAgentX | 652 | 82 | Python | 28 | Official implementation of AppAgentX: Evolving GUI Agents as Proficient Smartphone Users | 2025-04-15 |
| 42 | Awesome-Vibecoding-Guide | 643 | 70 | - | 1 | A compendium drawn from real commercial projects and hundreds of thousands of lines of AI‑assisted code. Read it end‑to‑end or feed this repo to your AI agent for summaries and Q&A. Stars and watches ... | 2026-01-27 |
| 43 | computer-agent | 640 | 77 | Rust | 5 | Desktop app to control your computer with AI using your terminal, browser, mouse & keyboard | 2026-01-09 |
| 44 | shell-analyzer | 596 | 98 | Java | 3 | 通过 JAVA AGENT 查杀内存马，提供简易方便的 GUI 界面，一键反编译目标环境内存马进行分析，支持远程查杀和本地查杀（注意：仅供本地复现分析学习，请勿用于正式和生产环境） | 2024-12-04 |
| 45 | OpenContext | 582 | 36 | JavaScript | 5 | A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenCode) with built‑in Skills/tools and a desktop GUI to capture, search, and reuse project kn... | 2026-01-30 |
| 46 | AgentPilot | 555 | 79 | Python | 2 | A versatile workflow automation platform to create, organize, and execute AI workflows, from a single LLM to complex AI-driven workflows. | 2026-04-14 |
| 47 | awesome-computer-use | 554 | 38 | - | 1 | This is a collection of resources for computer-use GUI agents, including videos, blogs, papers, and projects. | 2026-04-15 |
| 48 | Open-AgentRL | 520 | 50 | Python | 6 | [ICML 2026] RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings | 2026-05-16 |
| 49 | scarf | 519 | 32 | Swift | 3 | Native macOS and iOS App for the Hermes AI agent — multi-window, multi-server (local + remote over SSH). Chat, dashboard, sessions, memory, cron, MCP, and more. | 2026-05-17 |
| 50 | OS-Agent-Survey | 483 | 21 | - | 0 | This is the repo for the paper "OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use" (ACL 2025 Oral). | 2025-08-16 |
| 51 | AI-Coding-Style-Guides | 482 | 54 | JavaScript | 2 | A set of coding style guidelines for Vibe Coding or SWE-Agents that maximize efficiency and improve human readability. | 2025-09-15 |
| 52 | SeeClick | 481 | 31 | HTML | 3 | The model, data and code for the visual GUI Agent SeeClick | 2025-07-13 |
| 53 | OS-Atlas | 444 | 32 | Python | 19 | OS-ATLAS: A Foundation Action Model For Generalist GUI Agents | 2025-04-20 |
| 54 | ai-native-hiring-guide | 428 | 23 | HTML | 0 | AI-Native 工程师招聘面试官手册 · Builder / Reviewer 双岗评分 · AI 驾驶能力实操考核 · 易哈佛医疗 | 2026-03-12 |
| 55 | Awesome-GUI-Agents | 419 | 28 | - | 0 | A curated collection of resources, tools, and frameworks for developing GUI Agents. | 2026-05-13 |
| 56 | GUI-Actor | 407 | 51 | Python | 5 | [NeurIPS'25] GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents | 2026-04-13 |
| 57 | Aria-UI | 405 | 42 | Python | 5 | Open-sourced, Fast and Context-aware Action Grounding from GUI Instructions for GUI/Computer-use Agents | 2025-02-08 |
| 58 | aguvis | 391 | 29 | Python | 24 | [ICML2025] Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction | 2025-03-07 |
| 59 | pi-gui | 387 | 39 | TypeScript | 16 | Electron GUI app for the pi coding agent runtime | 2026-05-07 |
| 60 | LLM-Agent-Interview-Guide | 375 | 24 | - | 0 | 🔥 大模型 & Agent 面试八股文完全指南 | LLM & Agent Interview Preparation Guide | 2026-02-28 |
| 61 | agentboard | 370 | 42 | TypeScript | 4 | Web GUI for tmux optimized for AI agent TUIs, with support for iOS safari and mac w/ keyboard shortcuts | 2026-05-05 |
| 62 | agent-guides | 361 | 31 | Python | 0 | one page guides that i let my subscribed/customised agents consume to perform actions | 2025-06-20 |
| 63 | ai-agents-the-definitive-guide | 344 | 59 | Jupyter Notebook | 0 | Repo for AI Agents The Definitive Guide | 2026-03-26 |
| 64 | china-dictatroship-7 | 338 | 36 | HTML | 45 | 反中共政治宣传库。Anti Chinese government propaganda. https://github.com/cirosantilli/china-dictatorship 的备份backup. 住在中国真名用户的网友请别给星星，不然你要被警察请喝茶。常见问答集，新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件... | 2026-02-05 |
| 65 | hermes-optimization-guide | 318 | 22 | Shell | 0 | Hermes Agent setup, migration, LightRAG, Telegram, and skill creation guide | 2026-05-15 |
| 66 | EvoCUA | 317 | 23 | Python | 2 | EvoCUA: Evolving Computer Use Agent | 2026-03-31 |
| 67 | UGround | 315 | 18 | Python | 6 | [ICLR'25 Oral] UGround: Universal GUI Visual Grounding for GUI Agents | 2026-03-11 |
| 68 | openclaw-optimization-guide | 315 | 41 | TypeScript | 5 | Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context management, model selection, and one-shot development guide. | 2026-05-15 |
| 69 | AUITestAgent | 291 | 26 | - | 13 | AUITestAgent is the first automatic, natural language-driven GUI testing tool for mobile apps, capable of fully automating the entire process of GUI interaction and function verification. | 2024-07-19 |
| 70 | guild | 269 | 45 | Go | 25 | Shared context, memory, and task coordination across AI coding agents. Single Go binary, local SQLite, hybrid keyword and semantic search. | 2026-05-13 |
| 71 | Auto-GUI | 260 | 19 | Python | 9 | Official implementation for "You Only Look at Screens: Multimodal Chain-of-Action Agents" (Findings of ACL 2024) | 2024-07-16 |
| 72 | hermes-agent-guide | 249 | 57 | Python | 7 | Hermes Agent 是目前开源社区最具潜力的 AI Agent 框架之一。它继承了 OpenClaw 的优秀基因，在架构设计、记忆系统、技能生态和自动化能力上实现全面升级。但 Hermes 的文档分散在多个仓库和平台，缺乏一本系统性的中文指南。 本书填补的正是这个空白。全书 16 册、30 万+ 字，覆盖从安装部署到高阶开发、从个人玩赚到企业服务、从单 Agent 操控到多 Agent 编... | 2026-04-22 |
| 73 | GUI-R1 | 245 | 19 | Python | 9 | Official implementation of GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents | 2025-05-05 |
| 74 | autoclaw | 233 | 40 | TypeScript | 1 | AutoClaw is a hyper-lightweight AI agent designed to live inside Docker containers. Unlike heavy, GUI-dependent agents, AutoClaw is built for headless, massive-scale concurrency. | 2026-05-13 |
| 75 | LLM-Brained-GUI-Agents-Survey | 230 | 15 | CSS | 0 | GitHub page for "Large Language Model-Brained GUI Agents: A Survey" | 2025-06-23 |
| 76 | bespoke_automata | 222 | 23 | JavaScript | 7 | Bespoke Automata is a GUI and deployment pipline for making complex AI agents locally and offline | 2026-02-23 |
| 77 | guidance-for-personalized-ecommerce-recommendations-using-amazon-bedrock-agents | 215 | 13 | Python | 0 | This Guidance demonstrates how to implement personalized ecommerce recommendations using Amazon Bedrock Agents. | 2026-05-19 |
| 78 | OMG-Agent | 213 | 29 | Python | 3 | OMG-Agent: Open-sourced Mobile GUI Agent | 2025-12-28 |
| 79 | webqa-agent | 213 | 16 | Python | 19 | Autonomous web browser agent that audits performance, functionality & UX for engineers and vibe-coding creators. 网站自主评估测试 Agent，支持 GUI/CLI 一键完成性能、功能使用与交互体验的测试评估 | 2026-03-31 |
| 80 | EdgeBox | 201 | 26 | TypeScript | 2 | A fully-featured, GUI-powered local LLM Agent sandbox with complete MCP protocol support. Features both CLI and full desktop environment, enabling AI agents to operate browsers, terminal, and other ... | 2026-04-22 |
| 81 | EpicStaff | 198 | 28 | Python | 8 | Open-source platform for building AI agents with a visual UI and modular backend. | 2026-05-21 |
| 82 | cihna-dictattorshrip-8 | 197 | 23 | HTML | 27 | 反中共政治宣传库。Anti Chinese government propaganda. https://github.com/cirosantilli/china-dictatorship 的备份backup. 住在中国真名用户的网友请别给星星，不然你要被警察请喝茶。常见问答集，新闻集和饭店和音乐建议。卐习万岁卐。冠状病毒审查郝海东新疆改造中心六四事件法轮功 996.ICU709大抓捕巴拿马文件... | 2026-02-05 |
| 83 | OS-Genesis | 186 | 14 | Jupyter Notebook | 18 | [ACL 2025] Code and data for OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis | 2025-10-08 |
| 84 | OpenPacketFix_ | 183 | 18 | Java | 0 | 大陆修宪香港恶法台湾武统朝鲜毁约美中冷战等都是王沪宁愚弄习思想极左命运共同体的大策划中共窃国这半个多世纪所犯下的滔天罪恶，前期是毛泽东策划的，中期6.4前后是邓小平策划的，黄牛数据分析后期是毛的极左追随者三朝罪恶元凶王沪宁策划的。王沪宁高小肆业因文革政治和情报需要保送“学院外语班“红色仕途翻身，所以王的本质是极左的。他是在上海底层弄堂长大的，因其本性也促成其瘪三下三滥个性，所以也都说他有易主“变色... | 2022-08-12 |
| 85 | gameworld | 179 | 6 | Python | 0 | GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents | 2026-05-13 |
| 86 | infrastructure-agents-guide | 176 | 20 | - | 0 | How to design, build, and operate AI agents for infrastructure teams — safely. 13 chapters covering architecture, sandboxing, credentials, change control, observability, and more. | 2026-05-19 |
| 87 | openclaw-guide | 175 | 26 | PowerShell | 0 | 开源OpenClaw中文文档站，OpenClaw中文指南，支持小龙虾 AI 智能体安装部署、消息渠道接入、Agent 架构、Skills 技能配置、模型提供商、CLI 命令参考、网关运维、安全沙箱等全方位文档。覆盖 WhatsApp、Telegram、Discord、飞书、钉钉、企业微信等 20+ 聊天平台，OpenAI、Anthropic、Ollama、通义千问等 30+ LLM 提供商，Doc... | 2026-04-15 |
| 88 | Awesome-LLM-Powered-Phone-GUI-Agents | 171 | 9 | - | 1 | [TMLR] LLM-Powered GUI Agents in Phone Automation: Surveying Progress and Prospects | 2025-12-02 |
| 89 | dify-mcp-client | 168 | 32 | Python | 9 | MCP Client as an Agent Strategy Plugin. Support GUI operation via UI-TARS-SDK. | 2025-07-05 |
| 90 | OSWorld-G | 166 | 7 | TypeScript | 11 | [NeurIPS 2025 Spotlight] Scaling Computer-Use Grounding via UI Decomposition and Synthesis | 2025-11-06 |
| 91 | pgui | 164 | 20 | Rust | 0 | GUI app to query Postgres - Powered by GPUI | 2026-05-09 |
| 92 | os-ai-computer-use | 163 | 11 | Python | 2 | AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app ready. | 2026-03-17 |
| 93 | localLLM_guidance | 158 | 24 | Jupyter Notebook | 4 | Local LLM ReAct Agent with Guidance | 2023-05-23 |
| 94 | GUI-Odyssey | 158 | 9 | Python | 10 | [ICCV 2025] GUIOdyssey is a comprehensive dataset for training and evaluating cross-app navigation agents. GUIOdyssey consists of 8,834 episodes from 6 mobile devices, spanning 6 types of cross-app ta... | 2026-01-03 |
| 95 | ARPO | 158 | 11 | Python | 9 | Official Implementation of ARPO: End-to-End Policy Optimization for GUI Agents with Experience Replay | 2025-05-29 |
| 96 | awesome-mobile-agents | 156 | 12 | - | 2 | ✨✨Latest Papers and Datasets on Mobile and PC GUI Agent | 2024-11-29 |
| 97 | UI-R1 | 154 | 12 | Python | 0 | [AAAI-2026] Code for "UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning" | 2025-11-24 |
| 98 | Spider2-V | 152 | 16 | Jupyter Notebook | 1 | [NeurIPS 2024] Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows? | 2024-08-26 |
| 99 | mobile-use | 148 | 10 | Python | 11 | MobileUse: an open-source mobile GUI agent for Android phone automation, AndroidWorld/AndroidLab evaluation, hierarchical reflection, and proactive exploration. | 2026-05-07 |
| 100 | soteria | 147 | 13 | Rust | 3 | A GTK-based polkit authentication agent | 2026-04-01 |