Skip to main content
Runloop provides disposable devboxes for running code in isolated environments. See the Runloop docs for signup, authentication, and platform details.

​
Installation

pip install langchain-runloop

​
Create a sandbox backend

In Python, you create the devbox using the provider SDK, then wrap it with the deepagents backend. 
from runloop_api_client import RunloopSDK

from langchain_runloop import RunloopSandbox

api_key = "..."
client = RunloopSDK(bearer_token=api_key)

devbox = client.devbox.create()
backend = RunloopSandbox(devbox=devbox)

try:
    result = backend.execute("echo hello")
    print(result.output)
finally:
    devbox.shutdown()

​
Use with deepagents

from runloop_api_client import RunloopSDK
from langchain_anthropic import ChatAnthropic

from deepagents import create_deep_agent
from langchain_runloop import RunloopSandbox

api_key = "..."
client = RunloopSDK(bearer_token=api_key)

devbox = client.devbox.create()
backend = RunloopSandbox(devbox=devbox)

agent = create_deep_agent(
    model=ChatAnthropic(model="claude-sonnet-4-20250514"),
    system_prompt="You are a coding assistant with sandbox access.",
    backend=backend,
)

try:
    result = agent.invoke(
        {"messages": [{"role": "user", "content": "Create a small Python project and run tests"}]}
    )
finally:
    devbox.shutdown()

​
Cleanup

Always shut down devboxes when you are done to avoid ongoing resource usage. See also: Sandboxes.
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.