suitedaces/computer-agent

Desktop app to control your computer with AI using your terminal, browser, mouse & keyboard

What it solves

Taskhomie is a local AI agent designed to automate tasks across a computer's operating system. It allows users to provide natural language instructions to perform actions that would typically require manual human interaction with a desktop environment.

How it works

The agent operates in two distinct modes:

  • Computer Use Mode: The agent takes screenshots of the screen and directly controls the mouse cursor and keyboard to interact with any application.
  • Background Mode: This mode uses the Chrome DevTools Protocol for web automation and the terminal for other tasks, allowing the user to continue using their computer while the agent works asynchronously.

The system is built using Tauri and Rust for the backend and React for the frontend, utilizing Anthropic's models (Haiku, Sonnet, and Opus) to process instructions.

Who it’s for

Users looking to automate repetitive desktop tasks or research the capabilities of AI agents that can interact with a GUI and terminal.

Highlights

  • Dual-mode operation: Switch between full desktop control and non-intrusive background automation.
  • Cross-app automation: Ability to move the mouse, click, type, and run terminal commands across different software.
  • Native performance: Built with Rust and Tauri for efficient local execution.
  • Coded shortcuts: Integrated keyboard shortcuts for quick mode switching and agent control.

Related

  • Project
    shiwenwen/hope-agent

    Hope Agent is an open‑source, Rust‑based desktop AI assistant that can run as a native app, a headless server with a web UI, or an IDE‑integrated backend. It offers goal‑driven task automation, persistent memory, design‑space generation, and full computer control (file, shell, browser) with strong security (local‑first data, tool approval, Docker sandbox). Installable on macOS, Windows and Linux via package managers or Docker, it ships with dozens of LLM provider templates, multi‑platform IM integrations, and a plug‑in skill system.

  • Project
    netease-youdao/LobsterAI

    A desktop AI agent that automates office workflows by interacting with local files, terminal commands, and browser workflows through a dedicated runtime engine.

  • Project
    fluffypony/dothething

    A local AI agent that automates research, browser interaction, and system operations, featuring a specialized browser for bypassing bot detection and macOS computer use capabilities.

  • Project
    Eynzof/Hermes-CN-Desktop

    A native Windows and macOS desktop client for Hermes Agent, providing a streamlined interface and bundled runtime for managing AI agents.

  • Project
    bytedance/UI-TARS-desktop

    A multimodal AI agent stack that enables natural language control of desktop applications and web browsers through visual recognition and precise GUI interaction.