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
Prof-Harita/terminaI
TerminAI is a command line AI operator for Windows, Linux and macOS, written in TypeScript and running on Node.js. Instead of producing commands for the user to copy and paste, it inspects the machine, proposes a plan, and executes that plan through governed tools. Every run follows the same loop: intent, governed plan, approval, execution, audit. Risky actions are gated behind an approval ladder that the user configures, and the resulting actions are written to a local audit log so the change history can be reviewed afterwards. The agent drives a true pseudo-terminal, so it can work through interactive sessions that a plain command runner cannot handle, including sudo password prompts, ssh connections and full-screen programs such as vim or htop. Model choice is left open: it works with Gemini, OpenAI, any OpenAI-compatible endpoint, gateways such as OpenRouter, and locally hosted models, which allows a setup with no external charges and no telemetry. The documented use cases are system administration and general workflows rather than only coding, such as diagnosing an unstable graphics driver and proposing a clean reinstall, reviewing large files to free disk space, or running a recurring background check that writes results to a file and raises a system notification. The project is published as a public preview: the operator loop and the CLI are the stable surface, while desktop, voice and agent-to-agent remote features are optional and still being hardened. It is aimed at developers and technically confident general users who want an agent with real machine access but explicit control over what it is allowed to do.
https://github.com/Prof-Harita/terminaI
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.