Ui Automation Python Packages

pywinauto

Windows GUI Automation with Python (based on text properties)

2.7M 6K 787

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.

7K 6 0

aivane-agent-android

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

3K 9 1

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.

2K 7 0

pocket-desk-agent

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

2K 15 5

pywinauto-recorder

A record-replay tool to automate GUI via pywinauto

2K 195 38

devhelmkit

跨平台 UI 自动化框架，首期支持 HarmonyOS

1K 0 0

tarsier-ai

Semantic Desktop Automation Framework for AI Agents via Windows UI Automation.

1K 3 0

aivane-template-linter

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

1K 9 1

touchpoint-py

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

764 39 2

screenmonitormcp-v2

A revolutionary Model Context Protocol (MCP) server that gives AI real-time vision capabilities and enhanced UI intelligence power

359 71 18

pyscreenreader

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

328 4 0

mseep-screenmonitormcp-v2

A revolutionary Model Context Protocol (MCP) server that gives AI real-time vision capabilities and enhanced UI intelligence power

280 71 18

pyxtaf

Agentic Extensible Test Automation Framework

200 8 2

kira-mcp

Local MCP server for AI agents: local YOLO-based UI-element detection (OmniParser-v2 icon detector) with per-element OCR, hash caching, and full keyboard / mouse / screen / clipboard control via pyautogui + mss.

181 1 0

computeruseprotocol

Python SDK for the Computer Use Protocol

172 6 1

iflow-mcp-screenmonitormcp-v2

A revolutionary Model Context Protocol (MCP) server that gives AI real-time vision capabilities and enhanced UI intelligence power

143 71 18

virtualbox-helper

Python library to interact with a Virtualbox instance using simple computer vision

121 0 0

tdbot

RPA SDK by developers for developers

63 33 9