Skip to main content


This package creates an agent that uses XML syntax to communicate its decisions of what actions to take. It uses Anthropic's Claude models for writing XML syntax and can optionally look up things on the internet using DuckDuckGo.

Environment Setup​

Two environment variables need to be set:

  • ANTHROPIC_API_KEY: Required for using Anthropic


To use this package, you should first have the LangChain CLI installed:

pip install -U langchain-cli

To create a new LangChain project and install this as the only package, you can do:

langchain app new my-app --package xml-agent

If you want to add this to an existing project, you can just run:

langchain app add xml-agent

And add the following code to your file:

from xml_agent import agent_executor as xml_agent_chain

add_routes(app, xml_agent_chain, path="/xml-agent")

(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. You can sign up for LangSmith here. If you don't have access, you can skip this section

export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

This will start the FastAPI app with a server is running locally at http://localhost:8000

We can see all templates at We can access the playground at

We can access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/xml-agent")

Help us out by providing feedback on this documentation page: