ModalSandbox integration

Integrate with the ModalSandbox sandbox backend using LangChain Python.

Modal provides serverless container infrastructure with GPU support. See the Modal docs for signup, authentication, and platform details.

Installation

pip

pip install langchain-modal

uv add langchain-modal

Create a sandbox backend

In Python, you create the sandbox using the provider SDK, then wrap it with the deepagents backend.

import modal

from langchain_modal import ModalSandbox

app = modal.App.lookup("your-app")
modal_sandbox = modal.Sandbox.create(app=app)
backend = ModalSandbox(sandbox=modal_sandbox)

result = backend.execute("echo hello")
print(result.output)

Use with Deep Agents

import modal
from langchain_anthropic import ChatAnthropic

from deepagents import create_deep_agent
from langchain_modal import ModalSandbox

app = modal.App.lookup("your-app")
modal_sandbox = modal.Sandbox.create(app=app)
backend = ModalSandbox(sandbox=modal_sandbox)

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

result = agent.invoke(
    {"messages": [{"role": "user", "content": "Install numpy and calculate pi"}]}
)

Cleanup

You are responsible for managing the sandbox lifecycle via Modal. When you are done, terminate the sandbox.

See also: Sandboxes.

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.