CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
-
Updated
Feb 20, 2026 - Python
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
The Open Framework for autonomous virtual computer agents at scale, fully open-source, safe, auditable, and production-ready.
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.
Command Line telepathy. An Autonomous Al Agent for your Terminal that turns intent into Execution (Windows/Linux/Mac)
Official repository for paper: OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents
Desktop automation library for Ruby
Windows backend input automation library in Go (Message + HID). A Go wrapper over Interception for reliable Windows input automation. Ji Yu Nei He Qu Dong Ji De Windows RPA Zi Dong Hua Shu Ru Zhu Ru Ku
This project automates the conversion of Figma designs into code, supporting frameworks like Tkinter, Kivy, PyQt5, Java Swing, and C++ QT. It streamlines UI development by transforming design files into fully functional, customizable code while preserving the original layout, colors, fonts, and components.
Computer Use Protocol is a universal schema for AI agents to perceive and interact with any desktop UI.
V-Zen: Efficient GUI Understanding and Precise Grounding With A Novel Multimodal LLM Resources
Selenium WebDriver with Java from LetsKodeIt
Google Chrome offline game (T Rex) bot using Python.
Official Repo of "AI Agents for Computer Use: A Review of Instruction-based Computer Control, GUI Automation, and Operator Assistants"
Mouse Robot C#
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.
Add a description, image, and links to the gui-automation topic page so that developers can more easily learn about it.
To associate your repository with the gui-automation topic, visit your repo's landing page and select "manage topics."