Metadata

Sandbox metadata

Metadata is a way to attach arbitrary key-value pairs for a sandbox.

This is useful in various scenarios, for example:

• Associate a sandbox with a user session.
• Store custom user data for a sandbox like API keys.
• Associate a sandbox with a user ID and connect to it later.

You specify metadata when creating a sandbox and can access it later through listing running sandboxes with Sandbox.list() method.

The metadata parameter is a dictionary of key-value pairs.

Tip: Tip: See List Sandboxes for more information.

Python[Sync]

from agentbox import Sandbox

sandbox = Sandbox(
    api_key="ab_xxxxxxxxxxxxxxxxxxxxxxxxx",
    template="wemmodr8mb2uk3kn7exw",
    timeout=60,
    metadata={ 
    "user_id": "12345",  
    })

# List running sandboxes and access metadata.
running_sandboxes = Sandbox.list(api_key="ab_xxxxxxxxxxxxxxxxxxxxxxxxx")

print(running_sandboxes[0].metadata)
# Will print:
# {
#   'user_id': '12345',
# }

Python[Async]

from agentbox import AsyncSandbox

sandbox = await AsyncSandbox.create(
    api_key="ab_xxxxxxxxxxxxxxxxxxxxxxxxx",
    template="wemmodr8mb2uk3kn7exw",
    timeout=60,
    metadata={ 
    "user_id": "12345",  
    })

# List running sandboxes and access metadata.
running_sandboxes = await Sandbox.list(api_key="ab_xxxxxxxxxxxxxxxxxxxxxxxxx")

print(running_sandboxes[0].metadata)
# Will print:
# {
#   'user_id': '12345',
# }

Filtering sandboxes by metadata

You can also filter sandboxes by metadata, you can find more about it here