Havuz

Browser automation and computer use for AI agents. One CLI and MCP server for your signed-in browser, native macOS apps, and real iPhones.

Android automation from code. Test your apps on real phones, script the tasks you repeat, run a shelf of phones, or let an AI agent use one,

DeepSeek Harness plugin for Android — build, run, and interact with a live emulator or USB device stream inside a conversation, driven entir

DSH iOS, DeepSeek Harness içinden iOS Simulator ve USB ile bağlı iPhone üzerinde uygulama derleme, inceleme ve UI otomasyonu yapmayı sağlayan bir plugin'dir.

Neden yükseliyor · 39 günde 308 yıldız ve son 28 günde 16 commit dikkat çekiyor; ancak commit'lerin tek yazardan gelmesi topluluk katkısı ve bakım kapasitesi için henüz güçlü kanıt sunmuyor. İlgi, iOS geliştirme ve agent otomasyonunu tek bir akışta birleştirme vaadiyle açıklanabilir; bunun kullanımda ne kadar güvenilir olduğu verilen ölçümlerden doğrulanamıyor.

让 Claude、Codex、Cursor 等 AI 助手看懂 iPhone 屏幕并直接操作手机的 iOS 自动化工具与 MCP Server，支持 UI 树获取、元素定位、截图与 OCR 识别、点击滑动、文字输入、应用管理和日志读取，适用于自动化测试与 iOS 逆向调试

Give your AI agent eyes and hands on any desktop — cross-platform accessibility API with MCP server

Open-source desktop AI agent that sees what you see — one hotkey over any window, it answers, acts, or guides you step-by-step.

Reasonix 跨平台桌面自动化插件（重构版）。精准层优先（UIA/AXAPI/AT-SPI2）+ 视觉层兜底（EasyOCR），归一化坐标协议；Windows / Linux (X11) / macOS 三平台均已实现（同一套公共代码），Wayland 与未授权场景自动降级视

开源 Windows 本地 AI 工作台｜OpenAI-compatible + Claude CLI，99 个桌面/Office 工具，可回退文件操作与可视化多 Agent 工作流。

让 Agent 操控 Windows 桌面软件

Semantic UI automation and lightweight accessibility snapshots for LLM agents to interact with Web and Desktop applications.

Verified control of the whole desktop for agents on Windows and Linux: apps with no API, windows, shell, browser. MCP server + CLI + REST AP

Analyze jailbroken iOS and macOS apps, then build and verify independent implementations of selected behavior.

Windows computer-use MCP server: drive any desktop app via semantic discover-then-act targeting (entities + leases, not pixel coordinates),

Pi agent for Android — sideload the APK and run a Pi coding agent on your phone. Single-APK, on-device Termux runtime, Claude Pro/Max OAuth,

Fold, rotate and tap the iPhone Duo simulator from the command line — hinge, rotation and inner-screen touches for scripts and AI agents.

Open-source AI agent testing framework for browser and native desktop apps, with explicit tool effects, evidence, lifecycle, and trace contr

Voice-first desktop assistant for Windows — talk to your PC and it works inside real apps, safely. By VORNEX.

Claude plugin for auditing live web apps: capture screenshots, generate demo videos, document components, extract design tokens, map shadcn/

Let an AI see and operate Windows apps cheaply, without stealing focus or moving your mouse. MCP server for Claude Code.

MCP server for Android — drive emulators and real devices over adb from Claude Code, Cursor, or VS Code. 73 tools: screenshots, UI hierarchy

See and drive a GPUI app from the command line or MCP: snapshots with refs, clicks, typing, waits, screenshots and recordings