跳到主要内容
非官方简体中文翻译，内容版权归 Mastra 所有，遵循 Apache-2.0 许可。

AI SDK

If you're already using the Vercel AI SDK directly and want to add Mastra capabilities like processors or memory without switching to the full Mastra agent API, withMastra() lets you wrap any AI SDK model with these features. This is useful when you want to keep your existing AI SDK code but add input/output processing and conversation persistence, including content filtering.

提示

If you want to use Mastra together with AI SDK UI (e.g. useChat()), visit the AI SDK UI guide.

Installation
Installation的直接链接

Install @mastra/ai-sdk to begin using the withMastra() function.

npm install @mastra/ai-sdk@latest

Examples
Examples的直接链接

With Processors
With Processors的直接链接

Processors let you transform messages before they're sent to the model (processInput) and after responses are received (processOutputResult). This example creates a logging processor that logs message counts at each stage, then wraps an OpenAI model with it.

src/example.ts
import { openai } from '@ai-sdk/openai'
import { generateText } from 'ai'
import { withMastra } from '@mastra/ai-sdk'
import type { Processor } from '@mastra/core/processors'

const loggingProcessor: Processor<'logger'> = {
  id: 'logger',
  async processInput({ messages }) {
    console.log('Input:', messages.length, 'messages')
    return messages
  },
  async processOutputResult({ messages }) {
    console.log('Output:', messages.length, 'messages')
    return messages
  },
}

const model = withMastra(openai('gpt-5.4'), {
  inputProcessors: [loggingProcessor],
  outputProcessors: [loggingProcessor],
})

const { text } = await generateText({
  model,
  prompt: 'What is 2 + 2?',
})

With Memory
With Memory的直接链接

Memory automatically loads previous messages from storage before the LLM call and saves new messages after. This example configures a libSQL storage backend to persist conversation history, loading the last 10 messages for context.

src/memory-example.ts
import { openai } from '@ai-sdk/openai'
import { generateText } from 'ai'
import { withMastra } from '@mastra/ai-sdk'
import { LibSQLStore } from '@mastra/libsql'

const storage = new LibSQLStore({
  id: 'my-app',
  url: 'file:./data.db',
})
await storage.init()

const memoryStorage = await storage.getStore('memory')

const model = withMastra(openai('gpt-5.4'), {
  memory: {
    storage: memoryStorage!,
    threadId: 'user-thread-123',
    resourceId: 'user-123',
    lastMessages: 10,
  },
})

const { text } = await generateText({
  model,
  prompt: 'What did we talk about earlier?',
})

With Processors & Memory
With Processors & Memory的直接链接

You can combine processors and memory together. Input processors run after memory loads historical messages, and output processors run before memory saves the response.

src/combined-example.ts
import { openai } from '@ai-sdk/openai'
import { generateText } from 'ai'
import { withMastra } from '@mastra/ai-sdk'
import { LibSQLStore } from '@mastra/libsql'

const storage = new LibSQLStore({ id: 'my-app', url: 'file:./data.db' })
await storage.init()

const memoryStorage = await storage.getStore('memory')

const model = withMastra(openai('gpt-5.4'), {
  inputProcessors: [myGuardProcessor],
  outputProcessors: [myLoggingProcessor],
  memory: {
    storage: memoryStorage!,
    threadId: 'thread-123',
    resourceId: 'user-123',
    lastMessages: 10,
  },
})

const { text } = await generateText({
  model,
  prompt: 'Hello!',
})
  • withMastra(): API reference for withMastra()
  • Processors: Learn about input and output processors
  • Memory: Overview of Mastra's memory system
  • AI SDK UI: Using AI SDK UI hooks with Mastra agents, workflows, and networks
On this page