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
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.
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.
nut-tree/nut.js
nut.js is a cross-platform native UI automation and testing tool enabling keyboard, mouse, and image-based screen interactions for automating user interfaces.
BAAI-Agents/Cradle
Cradle is a framework that enables foundation AI models to perform complex computer tasks through human-like interaction using screenshots and keyboard/mouse controls, supporting various games and software applications.
e2b-dev/open-computer-use
Open Computer Use is a secure cloud Linux computer environment controlled by open-source large language models, enabling AI-driven operation via keyboard, mouse, and shell commands with live display streaming.
showlab/computer_use_ootb
Computer Use OOTB is an out-of-the-box GUI agent solution for Windows and macOS that enables desktop automation and remote control using API-based and local AI models with a user-friendly Gradio interface.
OpenCoworkAI/open-cowork
Open-source AI agent desktop application for Windows and macOS that wraps Claude Code, OpenAI, Gemini and other models in a GUI with VM sandboxing, MCP connectors and a skills system.
openkursar/hello-halo
Locally deployed AI workstation with a pluggable agent engine, scheduled autonomous workers, an embedded AI-controlled browser and remote control from enterprise chat clients.
mediar-ai/terminator
Terminator is a fast, reliable AI-native GUI automation tool for desktop applications on Windows, MacOS, and Linux, designed for AI agents and supporting multiple programming languages.
taracodlabs/aiden
Aiden is an autonomous work engine that plans multi-step jobs and executes them across files, terminal, browser and APIs, tracking evidence and verification for every effect it produces.
instavm/clickclickclick
ClickClickClick is an experimental Python framework that drives Android devices and macOS desktops autonomously from natural-language tasks, using paired planner and finder vision models.
jmerelnyc/Photo-agents
Photo Agents is a Python runtime for computer-using LLM agents built on a perceive-reason-act loop with vision-grounded layered memory, self-written skills, sandboxed execution and several desktop and chat frontends.
niuzaisheng/ScreenAgent
ScreenAgent is a computer control agent driven by a Visual Language Large Model that interacts with real computer screens through mouse and keyboard operations to complete multi-step tasks.
askui/vision-agent
AskUI Vision Agent is a multi-platform automation framework that enables secure and flexible native device automation using AI-driven UI commands and agentic instructions, designed for enterprise deployment.
CursorTouch/Windows-Use
Windows-Use is an open-source automation agent that enables AI-driven control of Windows OS by interacting directly with the GUI layer to perform tasks without relying on traditional computer vision models.
Prof-Harita/terminaI
Local-first CLI agent that operates the user machine through a real PTY, turning a stated intent into a governed plan, approval steps, execution and a local audit trail.
showlab/WorldGUI
WorldGUI is an interactive benchmark and agent framework that enables AI to automate desktop GUI tasks from any starting point using a self-reflective planning and execution mechanism.
showlab/assistgui
AssistGUI is an LLM-based desktop GUI assistant that automates operations in productivity software by controlling mouse and keyboard actions to enhance user efficiency.