Browser agent

readme: A browser agent with a dynamic, indexed action space.

description: ARTEMIS turns natural-language instructions into reliable Android automation.

readme: Each bot can use a cloud Linux desktop, an isolated Local VM, or

readme: Looks at the screen and finds buttons the way a person does: no app APIs, no per-app integration

readme: 用自然语言描述任务，助手就能打开 App、读取页面、点击、滚动、输入文字、整理列表，并在侧边栏展示手机屏幕。

description: Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model.

readme: Enable Claude Code, Codex, or any agent to use your real phone. The agent can scroll, tap, type, and read your phone

readme: It reads the accessibility tree and the screenshot, and aims on a labelled grid instead of doing coordinate maths

readme: the apps on your phone and the windows on your computer through their screens, for everything that never had an API.

readme: Desktop apps: read windows, click, type, and take screenshots.

readme: Agentic browser control, driven by the AI subscription you already pay for.

readme: Looks at the screen and finds buttons the way a person does: no app APIs, no per-app integration

readme: The agent plans the steps, uses Android Use to inspect pages, tap, swipe and enter text, then checks the result.

readme: 读屏、点击、滑动、输入（基于无障碍服务）；打开 App 或直接跳到指定页面。

readme: Mainplane drives your real browsers and applications with native computer use.

description: It sees the screen, clicks, types, browses and writes the code too.

description: 让 AI agent 直接查看、诊断、操作 运行在远程设备上的网页

description: Accessibility-first browser & computer use for AI agents

readme: It reads the accessibility tree and calls app APIs, runs shell commands, and operates the GUI when it needs to.

readme: Scout is an open-source agent that uses a real browser to finish a task for you.