new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

lmstudio/setup

4 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

LM Studio is OpenAI compatible

LM Studio is a user interface for running local models that contains an OpenAI compatible API server. It can be used with the AI SDK via the OpenAI compatible provider.

LM Studio installation

Install LM Studio provider using the @ai-sdk/openai-compatible module by running: npm install @ai-sdk/openai-compatible

LM Studio provider instance creation

Create a LM Studio provider instance using createOpenAICompatible from @ai-sdk/openai-compatible with name 'lmstudio' and baseURL 'http://localhost:1234/v1'. Example: const lmstudio = createOpenAICompatible({ name: 'lmstudio', baseURL: 'http://localhost:1234/v1' });

LM Studio default port

LM Studio uses port 1234 by default for the local server, but this can be changed in the app's Local Server tab.

Give your agent this brain