> ## Documentation Index
> Fetch the complete documentation index at: https://www.adaline.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Overview

# Gateway

Adaline Gateway is a single SDK to interact with 300+ LLMs. It runs entirely locally — no proxy, no data leaves your environment.

## Installation

```bash npm theme={null}
npm install @adaline/gateway @adaline/types @adaline/openai
```

```bash yarn theme={null}
yarn add @adaline/gateway @adaline/types @adaline/openai
```

```bash pnpm theme={null}
pnpm add @adaline/gateway @adaline/types @adaline/openai
```

## Quick Start

```typescript theme={null}
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

| Package | Description |
| - | - |
| `@adaline/gateway` | Core gateway SDK |
| `@adaline/types` | Shared types for config, messages, tools, etc. |
| `@adaline/openai` | OpenAI provider |
| `@adaline/anthropic` | Anthropic provider |
| `@adaline/google` | Google provider |
| `@adaline/azure` | Azure OpenAI provider |
| `@adaline/bedrock` | AWS Bedrock provider |
| `@adaline/groq` | Groq provider |
| `@adaline/togetherai` | Together AI provider |
| `@adaline/open-router` | Open Router provider |
| `@adaline/vertex` | Google Vertex provider |
| `@adaline/xai` | xAI provider |

## API Reference

> [card] [Gateway Class](https://www.adaline.ai/docs/reference/gateway/latest/classes/gateway.md)
>
> Core class for chat completions, streaming, embeddings, and tool calls.

> [card] [Types](https://www.adaline.ai/docs/reference/gateway/latest/types/config.md)
>
> Config, messages, tools, and response types.

> [card] [Examples](https://www.adaline.ai/docs/reference/gateway/latest/examples/complete-chat.md)
>
> Practical examples for common use cases.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.