Get your AI desktop agent running in 2 minutes
Visit the Template
Click the Deploy Now button in the Bytebot template on Railway.
Add Anthropic Key
Enter your ANTHROPIC_API_KEY
as the single required environment variable.
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.
Get your self-hosted AI desktop agent running with just three commands:
Clone and Configure
Start the Agent Stack
This starts all four services:
Open the Chat Interface
Navigate to http://localhost:9992 and start chatting!
Try asking:
First time? The initial startup may take 2-3 minutes as Docker downloads the images. Subsequent starts will be much faster.
You now have a fully functional AI agent that can:
Watch it work in real-time through the embedded VNC viewer in the tasks interface!
“Find the top 5 news stories about AI today and summarize them”
“Go to example.com and extract all email addresses into a list”
“Create a folder called ‘reports’ and organize files by date”
“Test the login flow on our staging site”
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 |
Computer API | http://localhost:9990/computer-use | Low-level desktop control API |
MCP SSE | http://localhost:9990/sse | Connect MCP clients for tool access |
If you just want the containerized desktop without the AI agent:
Or build locally:
Access the desktop at http://localhost:9990/vnc
If you just want the containerized desktop without the AI agent:
Or build locally:
Access the desktop at http://localhost:9990/vnc
Monitor what your agent is doing:
Remove all data and start fresh:
Container won't start
Check Docker is running and you have enough resources:
Can't connect to tasks UI
Ensure all services are running:
All services should show as “Up”.
Agent errors or no response
Check your API key is set correctly:
Understand how all the components work together
Deep dive into the AI agent capabilities
Build integrations with the REST APIs
Explore what others are building
Need help? Join our Discord community for support and to share what you’re building!
Get your AI desktop agent running in 2 minutes
Visit the Template
Click the Deploy Now button in the Bytebot template on Railway.
Add Anthropic Key
Enter your ANTHROPIC_API_KEY
as the single required environment variable.
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.
Get your self-hosted AI desktop agent running with just three commands:
Clone and Configure
Start the Agent Stack
This starts all four services:
Open the Chat Interface
Navigate to http://localhost:9992 and start chatting!
Try asking:
First time? The initial startup may take 2-3 minutes as Docker downloads the images. Subsequent starts will be much faster.
You now have a fully functional AI agent that can:
Watch it work in real-time through the embedded VNC viewer in the tasks interface!
“Find the top 5 news stories about AI today and summarize them”
“Go to example.com and extract all email addresses into a list”
“Create a folder called ‘reports’ and organize files by date”
“Test the login flow on our staging site”
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 |
Computer API | http://localhost:9990/computer-use | Low-level desktop control API |
MCP SSE | http://localhost:9990/sse | Connect MCP clients for tool access |
If you just want the containerized desktop without the AI agent:
Or build locally:
Access the desktop at http://localhost:9990/vnc
If you just want the containerized desktop without the AI agent:
Or build locally:
Access the desktop at http://localhost:9990/vnc
Monitor what your agent is doing:
Remove all data and start fresh:
Container won't start
Check Docker is running and you have enough resources:
Can't connect to tasks UI
Ensure all services are running:
All services should show as “Up”.
Agent errors or no response
Check your API key is set correctly:
Understand how all the components work together
Deep dive into the AI agent capabilities
Build integrations with the REST APIs
Explore what others are building
Need help? Join our Discord community for support and to share what you’re building!