What are the options to use NeMo Guardrails with Agents until Agent support is added?

[manuelschlegel]

I am currently looking for ways on how to integrate NeMo Guardrails in my Langchain Agents setup. As I understand the README, official Agent is coming soon, so I wanted to ask what options are already available now?

For example, would it be possible right now to "screen" the user input and the system output via NeMo Guardrails? How would I do that using Langchain? I envision it like this:

User Input -> User Input Screened by NeMo Guardrails -> Passed on to Agent -> System Output Screened by NeMo Guardrails -> System Output.

Thank you for your help.