There are 1 repository under gui-automation topic.
🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
AutoNode: A Neuro-Graphic Self-Learnable Engine for Cognitive GUI Automation
AutomationIDE , Python IDE creare by Python, Include [WEB, API, GUI, Load & Stress] automation.
A framework for GUI automation
Fully localized Robot Framework library for automating the SAP GUI using text locators
Nim GUI Automation Linux, simulate user interaction, mouse and keyboard.
V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM Resources
Selenium WebDriver with Java from LetsKodeIt
Wrapper around pyautogui - plus some new functions. Ideal for doing robotic process automation.
Mouse Robot C#
Automatically supply intelligent clicks to targeted kinds of pixel blocks in a dynamic canvas element.
Official Repo of "AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants"
Scan one-time-password generated on your mobile phone via webcam for use on your computer.
💻⌨🖱 Programmatically control the mouse & keyboard
A simple Automation bot for dropping trophies in Clash of Clans
This project automates the conversion of Figma designs into Python code, supporting frameworks like Tkinter, Kivy, and PyQt5. It streamlines UI development by transforming design files into fully functional, customizable Python code while preserving the original layout, colors, fonts, and components.
A Python-programmed bot using GUI Automation (PyAutoGUI library) and image recognition (OpenCV) that completely automated the process of queuing into and playing the video game Teamfight Tactics in order to earn tokens for rewards while I was not actively using my computer (ie. during the night).
Automate the typing process
An ongoing curated list of frameworks, books, articles, talks, screencasts, recordings, libraries, learning tutorials and resources about UI Testing & Best Practices Development
It asks for names. Using GUI Automation, opens MS-paint in Windows 10 and draws the names using brushes or pencils.
records keypresses and mouse clicks and exports as a Go program that does the same actions
Advanced MCP server for AI agents, computer use automation, and desktop operator control: Intelligent Window Management 🪟, Multi-Action Chaining ⛓️, AI-Optimized Screenshots 🖼️, macOS and Retina Display Support 🍎. Ideal for testing apps, games, and running desktop tasks locally with AI agents through Model Context Protocol.
A simple bot for Miscrits that helps you grind EXP by auto-attacking and capturing rare Miscrits using image recognition.
A simple GUI automation tool that uses a declarative YAML-based language. Instead of writing complex code, you can define your automation flows with clear and readable commands. It makes it easy to automate desktop tasks, from simple clicks and movements to opening applications, all within a single configuration file.
Code executor in python (send key in background, locate image, keyboard, mouse, discord, tor proxy, growtopia)
Python based GUI automation tool to do tedious repetitive tasks automatically, uses Tkinter and pyautogui.
This is Edmond 2.0, a Python-programmed bot using GUI Automation (PyAutoGUI library) and image recognition (OpenCV) that completely automated the entire “trading” process in my favorite video game, Realm of the Mad God.; facilitated game objectives including publishing trade offers, communicating with both sellers and buyers, selecting the items to trade, and confirming that the trade was legit. Recorded videos to continuously catch and fix bugs and improve the bot’s communication methods.
pyClicker is a Python program that automates mouse clicks. It utilizes the PyAutoGUI library to perform the clicking action and the keyboard library to start and stop the clicking process. Users can customize the start and stop buttons according to their preferences. With pyClicker, repetitive clicking tasks can be completed with ease.
A modifiable, Ruby-based Selenium3 project scaffold
A modular framework for benchmarking multimodal AI agents in a reproducible, full-OS environment. Using and adaption of the Smolagents's CodeAgent, Docker containers to run the VM in, VM's created using Qemu.
A WinAPI-based console application for detecting specific pixel colors on your screen and automating interactions.