LangChain integration
Use a Promigence sandbox as the backend of a LangChain Deep Agent, so the agent's shell commands and file edits happen in the sandbox. The same package adds a promigence sandbox provider to deepagents-code.
The package is langchain-promigence on PyPI, for Python.
Install
Install it and set your key.
pip install langchain-promigence
pip install "langchain-promigence[code]" # adds the deepagents-code provider
export PROMIGENCE_API_KEY=prom_api_...
export PROMIGENCE_SPEND_CAP=5
Example
From the guide Run LangChain Deep Agents in a Promigence sandbox, which goes on to the spend cap, cleaning up, and what the package does not support.
from deepagents import create_deep_agent
from langchain_promigence import PromigenceSandbox
sandbox = PromigenceSandbox.create(image="python:3.12-slim", working_dir="/workspace", spend_cap=1)
try:
agent = create_deep_agent(model="anthropic:claude-sonnet-4-5", backend=sandbox)
agent.invoke({"messages": [{"role": "user", "content": "run the tests and fix what fails"}]})
finally:
sandbox.kill()