​
Prerequisites

Before getting started with Bytebot, make sure you have:

  • Docker installed on your system
  • Sufficient system resources (recommended: 2+ CPU cores, 4GB+ RAM)
  • For the agent system: Docker Compose and an Anthropic API key

​
Running Bytebot

Getting started with Bytebot is simple and straightforward. You can run it as a standalone desktop container or as a full agent system with a chat UI.

​
Using the Computer Use API

The core functionality of Bytebot is programmatic control of the desktop environment through its API.

# Example: Move the mouse to coordinates (100, 200)
curl -X POST http://localhost:9990/computer-use \
  -H "Content-Type: application/json" \
  -d '{"action": "move_mouse", "coordinates": {"x": 100, "y": 200}}'

# Example: Take a screenshot

curl -X POST http://localhost:9990/computer-use \
 -H "Content-Type: application/json" \
 -d '{"action": "screenshot"}'

API Reference

View the complete Computer Use API documentation

​
Using the Agent Chat UI

When running the full agent system, you can interact with Bytebot through a chat interface that allows you to:

  1. Create and manage tasks
  2. Chat with the AI assistant
  3. View the desktop in real-time as the agent performs actions
  4. Monitor task progress and results

​
Next Steps

Now that you have Bytebot up and running, here are some next steps:

Explore the Architecture

Learn more about Bytebot’s architecture and components

Desktop Environment

Discover details about the containerized desktop environment

Agent System

Learn about the agent task management system

API Reference

Explore the Agent API for task management