How do you let the ACE_Framework for example Stacey demo run on a local llm instead of the online OpenAI?

[CRCODE22]

How do you let the ACE_Framework for example Stacey demo run on a local llm (local language model), instead of the online OpenAI?

I think a start would be:

https://github.com/Josh-XT/Local-LLM/
Local-LLM is a llama.cpp server in Docker with OpenAI Style Endpoints.
http://localhost:8091/v1

How would you let the ACE_Framework and the first demo I am trying to get to work is Stacey access that local OpenAI Endpoint instead of the online OpenAI? Or is there a better way to make the Stacey demo work locally with a local language model?