​
Bytebot Architecture

Bytebot is designed with a modular architecture that can be run as a standalone desktop container or as a full-featured agent system with a web UI.

​
Core Components

​
Container Base

  • Ubuntu 22.04 serves as the base operating system
  • Provides a stable foundation for the desktop environment and tools

​
Desktop Environment

  • XFCE4 desktop environment
  • Lightweight and customizable
  • Comes pre-configured with sensible defaults
  • Includes default user account: bytebot with sudo privileges

​
Automation Daemon (bytebotd)

  • bytebotd daemon is the core service that enables automation
  • Built on top of nutjs for desktop automation
  • Exposes a REST API for remote control
  • Provides unified endpoint for all computer actions
  • Accessible at localhost:9990

​
Browser and Tools

  • Firefox pre-installed and configured
  • Essential utilities for development and testing
  • Default applications for common tasks

​
Remote Access

  • VNC server for direct desktop access
  • noVNC for browser-based desktop access

​
Agent System Components

When running the full Bytebot system using docker-compose, the following additional components are available:

​
Bytebot Agent

  • Agent service that manages tasks and AI-driven automation
  • Built with NestJS for reliable API services
  • Implements a task processing system with queues via BullMQ
  • Integrates with Anthropic’s Claude for AI capabilities
  • Accessible at localhost:9991

​
Databases

  • PostgreSQL database for storing tasks, messages, and agent state
  • Redis for job queue management and caching
  • Provides persistence for tasks and conversations

​
Chat UI

  • NextJS web application for interacting with the agent
  • Provides a chat interface for communicating with the AI
  • Includes an embedded noVNC view for observing desktop actions
  • Accessible at localhost:9992

​
Task Management

The agent system implements a task-based workflow:

  1. Tasks are the primary unit of work with properties like status, priority, and description
  2. Messages represent the conversation between user and assistant
  3. Summaries capture the state and progress of tasks

​
Communication Flow

​
Standalone Mode

  1. External Application makes requests to the Bytebot API
  2. bytebotd daemon receives and processes these requests
  3. Desktop Automation is performed using nutjs
  4. Results/Screenshots are returned to the calling application

​
Agent Mode

  1. User creates tasks and sends messages via the Chat UI
  2. Agent service processes tasks and messages through a queue system
  3. AI Integration with Claude generates responses and computer actions
  4. Computer Use API executes actions on the Bytebot desktop
  5. Results are returned to the user through the Chat UI

​
Security Considerations

The default container configuration is intended for development and testing purposes only. It should not be used in production environments without security hardening.

Security aspects to consider before deploying in production:

  1. The container runs with a default user account that has sudo privileges
  2. Remote access protocols (VNC, noVNC) are not encrypted by default
  3. The REST API does not implement authentication by default
  4. Container networking exposes several ports that should be secured
  5. API keys (like ANTHROPIC_API_KEY) should be properly secured

​
Customization Points

Bytebot is designed to be customizable for different use cases:

  • Docker base image can be modified for different Linux distributions
  • Desktop environment can be replaced with alternatives (GNOME, KDE, etc.)
  • Pre-installed applications can be customized for specific testing needs
  • API endpoints can be extended for additional functionality
  • Agent system can be extended with custom tools and integrations