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
TurixAI/TuriX-CUA
TuriX is a computer-use agent that lets language and vision models take hands-on actions on a desktop, clicking, typing and navigating applications the same way a person would rather than calling app-specific APIs. Because it operates at the GUI level, it can drive tools that expose no automation interface, including WhatsApp, Excel, Outlook and in-house applications. The project is written mainly in Python and ships a macOS application plus branches covering Windows and Linux; the README documents a macOS 15+ quick start that requires a Python 3.12 environment and macOS Accessibility and Safari Automation permissions. The model behind the agent is configured in config.json and can be replaced without touching code, so users may run the bundled default policy or point it at their own provider, including Ollama and Qwen3-VL. TuriX exposes itself over the Model Context Protocol, which allows Claude for Desktop or any other MCP client to delegate desktop tasks to it. A skills mechanism lets users write markdown playbooks: a planner selects the relevant skill guide by name and description, and the acting model uses the full instructions to plan each step. The repository also contains OpenClaw skill packages for macOS and Windows so TuriX can be invoked from that agent runtime. On benchmarks the README reports 64.2 percent on the full OSWorld suite, described as third place on the leaderboard at 50 steps, and above 80 percent on a self-hosted OSWorld-style macOS benchmark, noting that no Linux training data was used. Later releases bundle the agent with a CLI and add separate office and coding execution modes. The project targets researchers and individual users who want an open, free desktop automation agent they can retarget to different models.
https://github.com/TurixAI/TuriX-CUA
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.
wonderwhy-er/DesktopCommanderMCP
Desktop Commander MCP is a server that integrates with the Claude desktop app to provide terminal control, file system search, and diff-based file editing capabilities, enabling advanced AI-assisted desktop management.
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.