Ui Automation Python Packages

pywinauto

Windows GUI Automation with Python (based on text properties)

tk-uia

Make Tkinter applications fully accessible to Windows screen readers and UI Automation: named, correctly typed, and activatable. One call, zero runtime dependencies.

sim-mirror

Mirror and drive iOS Simulators and real iPhones from Claude Code, any CLI agent or your browser — live viewer, agent cursor, token-efficient UI snapshots, screen recording and automation over MCP.

pctr

Element-based Windows UI Automation CLI for AI agents - find controls by name/type/id, not pixel coordinates. UIA + OCR + YOLO-World.

openadapt

Compiles a demonstrated GUI task into a program that reports VERIFIED only if an independent check agrees. pip install openadapt; openadapt flow tutorial. Compiler lives in openadapt-flow.

dsh-cua

Windows computer-use MCP server for dsh (DeepSeek Harness) — client-neutral, works with any stdio MCP client. Accessibility-first element actions, skyshot text trees, guarded raw input, and a cross-session arbiter that yields to the human.

wintegrate

CI-first Windows UI automation. Built for unattended runners, verified actions, and full diagnostic black-boxing.

macuitest

Drive macOS apps from Python, for end-to-end tests and AI agents

pywinauto-recorder

A record-replay tool to automate GUI via pywinauto

droidline

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, from Python, Node.js, the CLI, HTTP or Appium clients. No ADB, no USB cable, no root.

uitap

uiautomator2-style iOS UI automation client

mcp-phone-controll

The first MCP server for autonomous Flutter testing on real iPhones and Android devices. 110 tools across Android (uiautomator2+adb), iOS (WebDriverAgent+pymobiledevice3), Flutter (Patrol + flutter run --machine). Works with Claude Desktop, Claude Code, Cursor.

autourgos-cua-coordinate-tool

Vision based UI coordinate finder for Autourgos computer use agents

aivane-agent-android

AI mobile automation starter repo for AIVane. Android REPL beta, Python client, skills, examples, and protocol docs for AI agents.

pocket-desk-agent

Self-hosted Telegram bot — remote control your Windows PC with Gemini AI, OCR automation, live desktop streaming & scheduling.

win32-mcp-server

Comprehensive Windows automation MCP server for AI agents

devhelmkit

跨平台 UI 自动化框架，首期支持 HarmonyOS

pywinauto-core

Windows GUI Automation with Python (based on text properties)

tarsier-ai

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

screenforge

AI-driven cross-platform UI automation engine for Android, iOS, and Web. Your Agent inspects, decides, and acts — ScreenForge executes and generates pytest scripts with self-healing.

touchpoint-py

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

mat-uitest

AI 驱动的 UI 自动化测试工具：自然语言生成用例，混合定位 + 失败自愈，每一步留下可追溯证据（截图 / 控件树 / logcat / 失败分类）。执行全程在本机，离线可用。目前支持 Android 端和 iOS模拟器，其他端规划中。

pyscreenreader

PyScreenReader, parse on-screen information using the simplicity of Python on any platform.

aivane-template-linter

AI mobile automation starter repo for AIVane. Android REPL beta, Python client, skills, examples, and protocol docs for AI agents.