Quick Start#

Get up and running with AIO Sandbox in just a few minutes.

Prerequisites#

• Docker installed on your system
• At least 2GB of available RAM
• Port 8080 available (or use a different port mapping)

Installation#

Option 1: Run with Docker (Recommended)#

# Pull and run the latest version
docker run --rm -it -p 8080:8080 ghcr.io/agent-infra/sandbox:v1

Option 2: For Users in Mainland China#

Use our China mirror for faster downloads:

docker run --rm -it -p 8080:8080 enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:v1

Option 3: Custom Port Mapping#

If port 8080 is occupied, map to a different port:

docker run --rm -it -p 3000:8080 ghcr.io/agent-infra/sandbox:v1
# Then access via http://localhost:3000

First Launch#

After running the Docker command, you'll see the AIO Sandbox ASCII logo:

Access Points#

Once running, you can access different interfaces:

Quick Test#

1. Test the Browser#

Visit the VNC interface and interact with the desktop environment:

2. Test the Terminal#

Open your browser's developer console and connect to the WebSocket terminal:

const ws = new WebSocket('ws://localhost:8080/v1/shell/ws');
ws.onopen = () => {
  console.log('Terminal connected');
  ws.send(JSON.stringify({type: 'input', data: 'echo "Hello AIO Sandbox!"\n'}));
};
ws.onmessage = (event) => {
  const message = JSON.parse(event.data);
  console.log('Terminal output:', message);
};

3. Test File Operations#

Use the REST API to create a file:

curl -X POST http://localhost:8080/v1/file/write \
  -H "Content-Type: application/json" \
  -d '{
    "file": "/tmp/test.txt",
    "content": "Hello from AIO Sandbox!"
  }'

Then read it back:

curl -X POST http://localhost:8080/v1/file/read \
  -H "Content-Type: application/json" \
  -d '{"file": "/tmp/test.txt"}'

What's Next?#

Now that you have AIO Sandbox running:

1. Explore the Features: Check out our Features overview
2. Learn the APIs: Visit the API documentation for detailed interface specifications
3. Try Examples: See practical use cases in our Examples section
4. Integrate with Agents: Learn how to connect AI agents in our Agent Integration guide

Troubleshooting#

Common Issues#

Port already in use:

# Find what's using port 8080
lsof -i :8080

# Use a different port
docker run --rm -it -p 9000:8080 ghcr.io/agent-infra/sandbox:v1

Out of memory:

# Check available memory
docker stats

# Increase Docker memory limit in Docker Desktop settings

Connection refused:

# Make sure container is running
docker ps

# Check container logs
docker logs <container-id>

Getting Help#

• Check our troubleshooting guide for more solutions
• Browse examples for working code samples
• Review the API documentation for integration details

Ready to build something awesome? Let's dive deeper into the specific components!