AI SDK｜TypeScript 多模型 AI 应用与 Agent 开发工具包

access：来源确认 · npm install ai

project_type：来源确认 · is a provider-agnostic TypeScript toolkit designed to help you build AI-powered applications and agents

![hero illustration](https://github.com/vercel/ai/blob/HEAD/assets/hero.gif)

# AI SDK

The [AI SDK](https://ai-sdk.dev/docs) is a provider-agnostic TypeScript toolkit designed to help you build AI-powered applications and agents using popular UI frameworks like Next.js, React, Svelte, Vue, Angular, and runtimes like Node.js.

To learn more about how to use the AI SDK, check out our [API Reference](https://ai-sdk.dev/docs/reference) and [Documentation](https://ai-sdk.dev/docs).

## Installation

You will need Node.js 22+ and npm (or another package manager) installed on your local development machine.

```shell
npm install ai
```

## Skill for Coding Agents

If you use coding agents such as Claude Code or Cursor, we highly recommend adding the AI SDK skill to your repository:

```shell
npx skills add vercel/ai
```

## Unified Provider Architecture

The AI SDK provides a [unified API](https://ai-sdk.dev/docs/foundations/providers-and-models) to interact with model providers like [OpenAI](https://ai-sdk.dev/providers/ai-sdk-providers/openai), [Anthropic](https://ai-sdk.dev/providers/ai-sdk-providers/anthropic), [Google](https://ai-sdk.dev/providers/ai-sdk-providers/google), and [more](https://ai-sdk.dev/providers/ai-sdk-providers).

By default, the AI SDK uses the [Vercel AI Gateway](https://vercel.com/docs/ai-gateway) to give you access to all major providers out of the box. Just pass a model string for any supported model:

```ts
const result = await generateText({
  model: 'anthropic/claude-opus-5.5', // or 'openai/gpt-6-astra', 'google/gemini-3.8-flash', etc.
  prompt: 'Hello!',
});
```

You can also connect to providers directly using their SDK packages:

```shell
npm install @ai-sdk/openai @ai-sdk/anthropic @ai-sdk/google
```

```ts
import { anthropic } from '@ai-sdk/anthropic';

const result = await generateText({
  model: anthropic('claude-opus-5-5'), // or openai('gpt-6-astra'), google('gemini-3.8-flash'), etc.
  prompt: 'Hello!',
});
```

## Usage

### Generating Text

```ts
import { generateText } from 'ai';

const { text } = await generateText({
  model: 'openai/gpt-6-astra', // use Vercel AI Gateway
  prompt: 'What is an agent?',
});
```

### Generating Structured Data

```ts
import { generateText, Output } from 'ai';
import { z } from 'zod';

const { output } = await generateText({
  model: 'openai/gpt-6-astra',
  output: Output.object({
    schema: z.object({
      recipe: z.object({
        name: z.string(),
        ingredients: z.array(
          z.object({ name: z.string(), amount: z.string() }),
        ),
        steps: z.array(z.string()),
      }),
    }),
  }),
  prompt: 'Generate a lasagna recipe.',
});
```

### Agents

```ts
import { ToolLoopAgent } from 'ai';

const sandboxAgent = new ToolLoopAgent({
  model: 'openai/gpt-6-astra',
  system: 'You are an agent with access to a shell environment.',
  tools: {
    shell: openai.tools.localShell({
      execute: async ({ action }) => {
        const [cmd, ...args] = action.command;
        const sandbox = await getSandbox(); // Vercel Sandbox
        const command = await sandbox.runCommand({ cmd, args });
        return { output: await command.stdout() };
      },
    }),
  },
});
```

### UI Integration

The [AI SDK UI](https://ai-sdk.dev/docs/ai-sdk-ui/overview) module provides a set of hooks that help you build chatbots and generative user interfaces. These hooks are framework agnostic, so they can be used in Next.js, React, Svelte, and Vue.

You need to install the package for your framework, e.g.:

```shell
npm install @ai-sdk/react
```

#### Agent @/agent/image-generation-agent.ts

```ts
import { openai } from '@ai-sdk/openai';
import { ToolLoopAgent, InferAgentUIMessage } from 'ai';

export const imageGenerationAgent = new ToolLoopAgent({
  model: 'openai/gpt-6-astra',
  tools: {
    generateImage: openai.tools.imageGeneration({
      partialImages: 3,
    }),
  },
});

export type ImageGenerationAgentMessage = InferAgentUIMessage<
  typeof imageGenerationAgent
>;
```

#### Route (Next.js App Router) @/app/api/chat/route.ts

```tsx
import { imageGenerationAgent } from '@/agent/image-generation-agent';
import { createAgentUIStreamResponse } from 'ai';

export async function POST(req: Request) {
  const { messages } = await req.json();

  return createAgentUIStreamResponse({
    agent: imageGenerationAgent,
    messages,
  });
}
```

#### UI Component for Tool @/component/image-generation-view.tsx

```tsx
import { openai } from '@ai-sdk/openai';
import { UIToolInvocation } from 'ai';

export default function ImageGenerationView({
  invocation,
}: {
  invocation: UIToolInvocation<ReturnType<typeof openai.tools.imageGeneration>>;
}) {
  switch (invocation.state) {
    case 'input-available':
      return <div>Generating image...</div>;
    case 'output-available':
      return <img src={`data:image/png;base64,${invocation.output.result}`} />;
  }
}
```

#### Page @/app/page.tsx

```tsx
'use client';

import { ImageGenerationAgentMessage } from '@/agent/image-generation-agent';
import ImageGenerationView from '@/component/image-generation-view';
import { useChat } from '@ai-sdk/react';

export default function Page() {
  const { messages, status, sendMessage } =
    useChat<ImageGenerationAgentMessage>();

  const [input, setInput] = useState('');
  const handleSubmit = e => {
    e.preventDefault();
    sendMessage({ text: input });
    setInput('');
  };

  return (
    <div>
      {messages.map(message => (
        <div key={message.id}>
          <strong>{`${message.role}: `}</strong>
          {message.parts.map((part, index) => {
            switch (part.type) {
              case 'text':
                return <div key={index}>{part.text}</div>;
              case 'tool-generateImage':
                return <ImageGenerationView key={index} invocation={part} />;
            }
          })}
        </div>
      ))}

      <form onSubmit={handleSubmit}>
        <input
          value={input}
          onChange={e => setInput(e.target.value)}
          disabled={status !== 'ready'}
        />
      </form>
    </div>
  );
}
```

## Templates

We've built [templates](https://ai-sdk.dev/docs/introduction#templates) that include AI SDK integrations for different use cases, providers, and frameworks. You can use these templates to get started with your AI-powered application.

## Community

The AI SDK community can be found on [the Vercel Community](https://community.vercel.com/c/ai-sdk/62) where you can ask questions, voice ideas, and share your projects with other people.

## Contributing

Contributions to the AI SDK are welcome and highly appreciated. However, before you jump right into it, we would like you to review our [Contribution Guidelines](https://github.com/vercel/ai/blob/main/CONTRIBUTING.md) to make sure you have smooth experience contributing to AI SDK.

## Authors

This library is created by [Vercel](https://vercel.com) and [Next.js](https://nextjs.org) team members, with contributions from the [Open Source Community](https://github.com/vercel/ai/graphs/contributors).

Node.js 22+ 与 npm 或其他包管理器；需要模型提供商 API Key 或经由 Vercel AI Gateway 访问（默认路径），具体凭据配置待核验；模型调用与托管网关费用未在资料中给出，需向官方核验；是否依赖境外服务及境内可用性待核验。