Awesome AI AgentsDesktop Automation

bytebot-ai/bytebot

⭐ 11085 TypeScript added to this list on 2025-04-13 repository created 2025-02-03

Bytebot is a containerized Linux desktop environment designed to be controlled programmatically or accessed remotely, making it ideal for automation, web scraping, continuous integration tasks, and remote work scenarios. It runs an XFCE4 desktop on Ubuntu 22.04 within a single Docker image, providing a lightweight yet fully functional desktop experience. Users can interact with Bytebot through VNC or a browser-based noVNC interface, allowing access from anywhere without complex setup. The project offers a unified REST API that enables scripting of every mouse click, keystroke, and other desktop interactions, facilitating precise automation workflows. Bytebot comes pre-installed with essential tools including the Firefox browser, making it ready to use out of the box. The project supports quick startup via Docker commands or building and running locally with provided scripts. For more advanced use cases, Bytebot includes an alpha full agent stack that integrates with external APIs such as Anthropic's, enabling enhanced automation capabilities. The REST API supports a wide range of actions like moving the mouse, clicking, dragging, typing text, taking screenshots, and more, all controllable through simple HTTP requests. Bytebot is open source under the MIT license and encourages community contributions through a clear process involving forking, branching, and pull requests. The project is powered by the nutjs automation library and draws inspiration from Anthropic's computer-use demo. Comprehensive documentation and community support are available via the project's website, docs, Discord, and social media channels. Overall, Bytebot provides a versatile and accessible platform for building and running desktop agents in containerized environments, streamlining automation and remote desktop tasks.

https://github.com/bytebot-ai/bytebot

agent-stackagentic-aiagentsai-agentsai-toolsanthropicanthropic-apiautomationbytebotci-taskscomputer-usecontainerized-desktopcuadesktop-agentsdockerfirefoxgeminikeyboard-controllinux-desktopllmmit-licensemouse-controlnovncnutjsopen-sourceopenaipre-installed-toolsremote-workrest-apiscrapingscriptingubuntu-22.04vncxfce4

Also in Desktop Automation

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.

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.

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.