mobile-agent

An on-device AI agent for Android that operates apps and the web to get things done for you.

Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.

nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.

PhoneClaw turns phones into local AI agent runtimes with on-device models, native mobile Skills, LiveLand, and optional Mac Gateway inference.

[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training

Run the DeepSeek Harness AI agent natively on Android — no root, no Termux, extension center included | 手机本地运行 DeepSeek Agent，免 Root 免 Termux

Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows.

MobileUse: an open-source mobile GUI agent for Android phone automation, AndroidWorld/AndroidLab evaluation, hierarchical reflection, and proactive exploration.

An agent-first mobile runtime built on OpenClaw: control apps, learn reusable skills, and connect phones.

Autonomous on-device Android AI agent powered by pure vision (13MB APK). Runs 100% natively on a background virtual display—no root, no PC, no Accessibility Service, and no Termux/Linux sandbox needed. Just pair once via Wireless Debugging, add your API key, and go.

AI-powered mobile automation agent — describe what you want in plain English, AppClaw reads the screen, reasons, and acts. LLM-agnostic, open-source, zero telemetry.

[ECCV 2026] Official Repository for "DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents"

MuseLite is an open-source AI workspace combining chat, Agent tools, browser automation, and scheduled tasks for users who enjoy Muse and Dots.

Official code for "Relevance Does Not Imply Applicability: Experience Activation for Personal GUI Agents".

Open-source Android phone-use agent. Your phone, on autopilot.

gWorld: open-weight GUI world model (8B/32B) for mobile GUI agents — predicts the next screen as renderable HTML. ICML 2026.

把你的手机变成 AI 手机：一个住在手机里的 Personal Agent，交代一句就替你办好。Turn your phone into an AI phone.

An iPhone app where an LLM controls the phone it runs on (no Mac required after setup)