LangChain kit

ChatOpenAI accepts a custom base URL — both patterns from the OpenAI SDK kit apply.

JS/TS

npm i @langchain/openai @langchain/core

import { ChatOpenAI } from "@langchain/openai";

// Through the gateway: cascade + cooldowns included
const llm = new ChatOpenAI({
  model: "auto",
  apiKey: "local",
  configuration: { baseURL: "http://localhost:8787/v1" },
});

const reply = await llm.invoke("One-line summary of CRDTs");

Full kit — ModelHubby Indie

The rest of this kit — the full framework wiring, working code, and the edge cases it already survived — ships with the Indie field library. What you’ve read above is the real first section, not a blurred preview; the remainder simply isn’t in this page.