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

open-responses/setup

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

Open Responses provider package

The Open Responses provider is available as the `@ai-sdk/open-responses` module.

createOpenResponses configuration

Create an Open Responses provider instance using `createOpenResponses` with required options `name` (string used in model's provider identifier and as key for provider options) and `url` (full URL for the Open Responses API POST endpoint, like http://localhost:1234/v1/responses, not just base URL). Optional settings include: apiKey (string, sent as bearer token in Authorization header), headers (Record<string,string> for custom headers), and fetch (custom fetch implementation).

Open Responses protocol specification

Open Responses is an open specification based on the OpenAI Responses API, used for connecting AI SDK Core to language model servers that implement an Open Responses-compatible POST endpoint.

LM Studio endpoint example

For a local LM Studio server without authentication, configure with name 'lmstudio' and url 'http://localhost:1234/v1/responses'.

OpenAI Responses API endpoint example

For the OpenAI Responses API, configure with name 'openai', url 'https://api.openai.com/v1/responses', and apiKey set to the OPENAI_API_KEY environment variable.

When to use Open Responses vs OpenAI provider

Use @ai-sdk/open-responses for third-party or self-hosted endpoints that implement the Open Responses protocol, such as LM Studio. If you call OpenAI directly and need OpenAI-specific provider options or built-in tools, use the @ai-sdk/openai provider instead.

Give your agent this brain