​
Host Bytebot on Railway

​
☁️ One-click Deploy on Railway

Deploy on Railway
1

Visit the Template

Click the Deploy Now button in the Bytebot template on Railway.
2

Add Anthropic Key

Enter either your ANTHROPIC_API_KEY, OPENAI_API_KEY, or GOOGLE_API_KEY for the bytebot-agent resource.
3

Deploy & Launch

Hit Deploy. Railway will build the stack, wire the services together via private networking and output a public URL for the UI. Your agent should be ready within a couple of minutes!
Need more details? See the full Railway deployment guide.

​
Self-host Bytebot

​
Prerequisites

  • Docker ≥ 20.10
  • Docker Compose
  • 4GB+ RAM available
  • AI API key from one of these providers:

​
🚀 2-Minute Setup

Get your self-hosted AI desktop agent running with just three commands:
1

Clone and Configure

git clone https://github.com/bytebot-ai/bytebot.git
cd bytebot

# Configure your AI provider (choose one):
echo "ANTHROPIC_API_KEY=your_api_key_here" > docker/.env    # For Claude
# echo "OPENAI_API_KEY=your_api_key_here" > docker/.env     # For OpenAI
# echo "GOOGLE_API_KEY=your_api_key_here" > docker/.env     # For Gemini
2

Start the Agent Stack

docker-compose -f docker/docker-compose.yml up -d
This starts all four services:
  • Bytebot Desktop: Containerized Linux environment
  • AI Agent: Claude-powered task processor
  • Chat UI: Web interface for interaction
  • Database: PostgreSQL for persistence
3

Open the Chat Interface

Navigate to http://localhost:9992 and start chatting!Try asking:
  • “Open Firefox and search for the weather forecast”
  • “Take a screenshot of the desktop”
  • “Create a text file with today’s date”
First time? The initial startup may take 2-3 minutes as Docker downloads the images. Subsequent starts will be much faster.

​
What Just Happened?

You now have a fully functional AI agent that can:
  • 🖱️ Control mouse and keyboard
  • 🌐 Browse the web
  • 📄 Create and edit documents
  • 📧 Manage emails
  • 🔄 Automate any desktop task
Watch it work in real-time through the embedded VNC viewer in the tasks interface!

​
Try These Example Tasks

Web Research

“Find the top 5 news stories about AI today and summarize them”

Data Collection

“Go to example.com and extract all email addresses into a list”

File Management

“Create a folder called ‘reports’ and organize files by date”

Testing

“Test the login flow on our staging site”

​
Accessing Your Services

ServiceURLPurpose
Tasks UIhttp://localhost:9992Main interface for interacting with the agent
Agent APIhttp://localhost:9991/tasksREST API for programmatic task creation
Computer APIhttp://localhost:9990/computer-useLow-level desktop control API
MCP SSEhttp://localhost:9990/mcpConnect MCP clients for tool access

​
Alternative Deployment Options

If you just want the containerized desktop without the AI agent:
#Using pre-built image (recommended)
docker-compose -f docker/docker-compose.core.yml pull
docker-compose -f docker/docker-compose.core.yml up -d
Or build locally:
docker-compose -f docker/docker-compose.core.yml up -d --build
Access the desktop at http://localhost:9990/vnc

​
Managing Your Agent

​
View Logs

Monitor what your agent is doing: 
# All services
docker-compose -f docker/docker-compose.yml logs -f

# Just the agent
docker-compose -f docker/docker-compose.yml logs -f bytebot-agent

​
Stop Services

docker-compose -f docker/docker-compose.yml down

​
Update to Latest

docker-compose -f docker/docker-compose.yml pull
docker-compose -f docker/docker-compose.yml up -d

​
Reset Everything

Remove all data and start fresh: 
docker-compose -f docker/docker-compose.yml down -v

​
Quick API Examples

​
Create a Task via API

curl -X POST http://localhost:9991/tasks \
  -H "Content-Type: application/json" \
  -d '{
    "description": "Search for flights from NYC to London next month",
    "type": "browser_task"
  }'

​
Direct Desktop Control

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

# Type text
curl -X POST http://localhost:9990/api/computer \
  -H "Content-Type: application/json" \
  -d '{"action": "type_text", "text": "Hello, Bytebot!"}'

​
Troubleshooting

​
Next Steps

Architecture Overview

Understand how all the components work together

Agent System

Deep dive into the AI agent capabilities

API Reference

Build integrations with the REST APIs

Use Cases

Explore what others are building
Need help? Join our Discord community for support and to share what you’re building!