bytedance/UI-TARS-desktop
UI-TARS Desktop is a GUI Agent application that uses a Vision-Language Model to enable natural language control of computers across multiple platforms with real-time visual recognition and automation capabilities.
Awesome AI Agents › Desktop Automation
wonderwhy-er/DesktopCommanderMCP
Desktop Commander MCP is a server designed to integrate with the Claude desktop app, providing it with advanced terminal control, file system search, and diff-based file editing capabilities. It enables users to execute terminal commands with output streaming, manage processes, and handle long-running commands efficiently. The server supports session management, command timeout, and background execution, making it suitable for complex and extended terminal operations. The project is built on top of the Model Context Protocol (MCP) and extends the MCP Filesystem Server to offer enhanced file management features. Users can perform full filesystem operations such as reading and writing files, creating and listing directories, moving files and directories, searching files by name, and retrieving detailed file metadata. It also supports code editing with surgical text replacements for minor changes and full file rewrites for major modifications, including pattern-based replacements and multi-file support. One of the standout features is the integration of vscode-ripgrep for recursive code or text search within folders, providing powerful and efficient search capabilities. The server also supports reading files from URLs, including both text and images, with visual display and analysis capabilities within Claude's interface. Installation is flexible, offering multiple options such as using npx, a bash script installer for macOS, Smithery integration, manual configuration, or local checkout and build. The server automatically updates when installed via npx or Smithery, ensuring users have the latest features and fixes. The project emphasizes security by allowing configuration management with settings like blocked commands, default shell selection, and allowed directories for file operations. It provides comprehensive tools categorized into configuration, terminal, filesystem, and text editing, each with detailed commands and usage examples. Overall, Desktop Commander MCP enhances the Claude desktop app by enabling robust terminal and file system interactions, making it a powerful tool for developers and power users who need to manage their desktop environment through AI-assisted commands and file operations.
https://github.com/wonderwhy-er/DesktopCommanderMCP
Also in Desktop Automation
asweigart/pyautogui
PyAutoGUI is a cross-platform Python module that enables programmatic control of the mouse and keyboard for GUI automation, including features like screen capture and image recognition.
bytebot-ai/bytebot
Bytebot is a containerized Linux desktop environment that enables programmatic control and remote access for automation, scraping, CI tasks, and remote work through a unified REST API and VNC interfaces.
OthersideAI/self-operating-computer
The Self-Operating Computer Framework enables multimodal AI models to autonomously operate a computer by interpreting screen visuals and executing mouse and keyboard actions to achieve user-defined objectives.
jacklandrin/OnlySwitch
OnlySwitch is a customizable all-in-one macOS menu bar app that consolidates system toggles, shortcuts, and AI-powered controls to enhance user productivity and convenience.
iflytek/astron-rpa
AstronRPA is an enterprise-grade open-source Robotic Process Automation desktop application that enables low-code/no-code workflow automation for desktop and web applications with strong enterprise security, collaboration, and AI agent integration.
yuruotong1/autoMate
autoMate is an AI-driven local automation assistant that uses natural language commands to enable users to automate complex computer tasks without programming, supporting local deployment and full interface control for enhanced privacy and flexibility.
TurixAI/TuriX-CUA
Open-source computer-use agent that performs real GUI actions on macOS and Windows desktops, with swappable vision-language model backends and MCP access for other agents.