LM Studio

A local LM Studio server exposing an OpenAI-compatible endpoint, selected with LLM_PROVIDER=lmstudio, used to extract facts from conversations.

Enable it

LLM_PROVIDER=lmstudio
OPENAI_BASE_URL=http://localhost:1234/v1
OPENAI_LLM_MODEL=<model-loaded-in-lm-studio>
# No API key: LM Studio runs locally with no auth.

Configuration

Variable	Default	Description
LLM_PROVIDER	openai	Set to lmstudio.
OPENAI_BASE_URL	https://api.openai.com/v1	Point at your LM Studio server: http://localhost:1234/v1.
OPENAI_LLM_MODEL	gpt-4.1-nano	The model loaded in LM Studio.
OPENAI_API_KEY	(none)	Not required; the local server has no auth.

Notes

• OpenAI-compatible: the provider reuses the OpenAI request handling and only differs by base URL and model.
• Local server with no authentication, so no API key is needed.
• You must override OPENAI_BASE_URL to your LM Studio address; its default points at OpenAI.