Langchain Agent supports

[ravisamavedula]

How we can add Nemo Guardrails in Langchain Agents.
from langchain.agents import create_agent
agent = create_agent("gpt-5", tools=tools)

Its has support for middleware,
before_agent - Before agent starts (once per invocation)
before_model - Before each model call
after_model - After each model response
after_agent - After agent completes (once per invocation)

is this the place we shall add, please suggest the approach.