​

Gateway

​

Installation

npm install @adaline/gateway @adaline/types @adaline/openai

​

Quick Start

import { Gateway } from "@adaline/gateway";
import { OpenAI } from "@adaline/openai";
import { Config, MessageType } from "@adaline/types";

// Initialize gateway and model
const gateway = new Gateway();
const openai = new OpenAI();
const gpt4o = openai.chatModel({ modelName: "gpt-4o", apiKey: process.env.OPENAI_API_KEY });

// Complete a chat
const response = await gateway.completeChat({
  model: gpt4o,
  config: Config().parse({ temperature: 0.7, maxTokens: 300 }),
  messages: [{ role: "user", content: [{ modality: "text", value: "Hello!" }] }],
  tools: [],
});

console.log(response);

​

Key Features

• Unified interface — One API for OpenAI, Anthropic, Google, Azure, Bedrock, Groq, Together AI, Open Router, Vertex, XAI, and custom providers
• Fully local — No proxy server, no data leaves your environment
• Streaming — First-class async generator support for streaming responses
• Embeddings — Generate embeddings across providers with a single interface
• Tool calls — Execute tool calls returned by LLMs
• Plugins — Pluggable cache, HTTP client, logger, and queue backends
• Batching & retries — Built-in configurable queues with automatic retry and exponential backoff
• OpenTelemetry — Native telemetry integration
• Isomorphic — Works in Node.js and browsers (with dangerouslyAllowBrowser)

​

Packages

​

API Reference