Choose Your Deployment Method

Bytebot can be deployed in several ways depending on your needs:

Railway (Easiest)
Docker Compose
Kubernetes/Helm
Desktop Only

☁️ One-click Deploy on Railway

Visit the Template

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

Add Anthropic Key

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

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 with Docker Compose

Prerequisites

Docker ≥ 20.10
Docker Compose
4GB+ RAM available
AI API key from one of these providers:
- Anthropic (get one here) - Claude models
- OpenAI (get one here) - GPT models
- Google (get one here) - Gemini models

🚀 2-Minute Setup

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

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 "GEMINI_API_KEY=your_api_key_here" > docker/.env     # For Gemini

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: LLM-powered task processor (supports Claude, GPT, or Gemini)
Chat UI: Web interface for interaction
Database: PostgreSQL for persistence

Open the Chat Interface

Navigate to http://localhost:9992 to access the Bytebot UI.Two ways to interact:

Tasks: Enter task descriptions to have Bytebot work autonomously
Desktop: Direct access to the virtual desktop for manual control

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 You Just Deployed

You now have a complete AI desktop automation system with:

🔐 Password Manager Support: Bytebot can handle authentication automatically when you install a password manager extension. See our password management guide for setup instructions.

AI Agent

Understands natural language
Plans and executes tasks
Adapts to errors
Works autonomously

Virtual Desktop

Full Ubuntu environment
Browser, office tools
File system access
Application support

Task Interface

Create and manage tasks
Real-time desktop view
Conversation history
Takeover mode

REST APIs

Programmatic control
Task management API
Direct desktop access
MCP protocol support

🚀 Your First Tasks

Now let’s see Bytebot in action! Try these example tasks:

Simple Tasks (Test the Basics)

Take a Screenshot

“Take a screenshot of the desktop”

Open Browser

“Open Firefox and go to google.com”

Create File

“Create a text file called ‘hello.txt’ with today’s date”

System Info

“Check the system information and tell me the OS version”

Advanced Tasks (See the Power)

Web Research

“Find the top 5 AI news stories today and create a summary document”

Data Extraction

“Go to hacker news, find the top 10 stories, and save them to a CSV file”

Document Processing

“Upload a PDF contract and extract all payment terms and deadlines”

Multi-Step Workflow

“Search for ‘machine learning tutorials’, open the first 3 results in tabs, and take screenshots of each”

Accessing Your Services

Service	URL	Purpose
Tasks UI	http://localhost:9992	Main interface for interacting with the agent
Agent API	http://localhost:9991/tasks	REST API for programmatic task creation
Desktop API	http://localhost:9990/computer-use	Low-level desktop control API
MCP SSE	http://localhost:9990/mcp	Connect MCP clients for tool access

🖥️ Desktop Container Only

If you just want the virtual 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

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

# Task with file upload
curl -X POST http://localhost:9991/tasks \
  -F "description=Read this contract and summarize the key terms" \
  -F "priority=HIGH" \
  -F "[email protected]"

Direct Desktop Control

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

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

Troubleshooting

Container won't start

Check Docker is running and you have enough resources:

docker info
docker-compose -f docker/docker-compose.yml logs 

Can't connect to tasks UI

Ensure all services are running:

docker-compose -f docker/docker-compose.yml ps

All services should show as “Up”.

Agent errors or no response

Check your API key is set correctly:

cat docker/.env
docker-compose -f docker/docker-compose.yml logs bytebot-agent 

Ensure you’re using a valid API key from Anthropic, OpenAI, or Google.

📚 Next Steps

Using the UI

Learn how to create and manage tasks effectively

Takeover Mode

Take control when you need to guide Bytebot

LiteLLM Integration

Use any LLM provider with Bytebot

API Integration

Automate Bytebot with your applications

🔧 Configuration Options

Environment Variables

AI Provider Settings

# Choose one AI provider:
ANTHROPIC_API_KEY=sk-ant-...    # For Claude models
OPENAI_API_KEY=sk-...           # For GPT models  
GEMINI_API_KEY=...              # For Gemini models

# Optional: Use specific models
ANTHROPIC_MODEL=claude-3-5-sonnet-20241022  # Default
OPENAI_MODEL=gpt-4o
GEMINI_MODEL=gemini-1.5-flash

Port Configuration

# Change default ports if needed
# Edit docker-compose.yml ports section:
# bytebot-ui:
#   ports:
#     - "8080:9992"  # Change 8080 to your desired port

Using LiteLLM Proxy

# To use multiple LLM providers, use the proxy setup:
docker-compose -f docker/docker-compose.proxy.yml up -d

# This includes a pre-configured LiteLLM proxy

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

​Choose Your Deployment Method

​☁️ One-click Deploy on Railway

​🐳 Self-host with Docker Compose

​Prerequisites

​🚀 2-Minute Setup

​🎯 What You Just Deployed

AI Agent

Virtual Desktop

Task Interface

REST APIs

​🚀 Your First Tasks

​Simple Tasks (Test the Basics)

Take a Screenshot

Open Browser

Create File

System Info

​Advanced Tasks (See the Power)

Web Research

Data Extraction

Document Processing

Multi-Step Workflow

​Accessing Your Services

​☸️ Deploy with Helm

​🖥️ Desktop Container Only

​Managing Your Agent

​View Logs

​Stop Services

​Update to Latest

​Reset Everything

​Quick API Examples

​Create a Task via API

​Direct Desktop Control

​Troubleshooting

​📚 Next Steps

Using the UI

Takeover Mode

LiteLLM Integration

API Integration

​🔧 Configuration Options

​Environment Variables

Choose Your Deployment Method

☁️ One-click Deploy on Railway

🐳 Self-host with Docker Compose

Prerequisites

🚀 2-Minute Setup

🎯 What You Just Deployed

🚀 Your First Tasks

Simple Tasks (Test the Basics)

Advanced Tasks (See the Power)

Accessing Your Services

☸️ Deploy with Helm

🖥️ Desktop Container Only

Managing Your Agent

View Logs

Stop Services

Update to Latest

Reset Everything

Quick API Examples

Create a Task via API

Direct Desktop Control

Troubleshooting

📚 Next Steps

🔧 Configuration Options

Environment Variables