Vercel AI SDK

The Vercel AI SDK adapter wires MemexAI memory tools into any generateText, streamText, or generateObject call.

Before you start

Choose service mode or direct Postgres mode.
Read How MemexAI works for the tool-call-to-Postgres flow.
Read Memory tools to choose agentic tools or raw file tools.
Read Memory scopes before writing paths like user/profile.md.

Install

npm install @memexai/sdk ai

For direct Postgres mode:

npm install @memexai/core ai

Service mode (recommended)

Use @memexai/sdk when connecting to the containerized MemexAI service.

import { MemexAI } from '@memexai/sdk'
import { generateText, stepCountIs } from 'ai'
import { createGoogleGenerativeAI } from '@ai-sdk/google'

const memex = new MemexAI({ url: 'http://localhost:8080', apiKey: process.env.MEMEX_API_KEY! })
const memory = memex.forUser({ userId: 'user_123', actor: 'assistant' })
const system = await memory.getSystemPrompt('You are a helpful assistant with durable user memory.')

const result = await generateText({
  model: createGoogleGenerativeAI()('gemini-2.5-flash'),
  system,
  prompt: 'Remember that I prefer quiet neighborhoods near good schools.',
  tools: memory.createAgenticToolset(),
  stopWhen: stepCountIs(5),
})

console.log(result.text)

The instance method memory.createAgenticToolset() returns Vercel AI-compatible tools directly. Pair it with memory.getSystemPrompt(...) so stored memory can influence the next response.

Direct Postgres mode

Use @memexai/core when your app owns the Postgres connection.

import { createMemex } from '@memexai/core'
import { generateText, stepCountIs } from 'ai'
import { createGoogleGenerativeAI } from '@ai-sdk/google'

const google = createGoogleGenerativeAI()
const memex = createMemex({ databaseUrl: process.env.DATABASE_URL!, model: google('gemini-2.5-flash') })
await memex.migrate()

const memory = memex.forUser({ userId: 'user_123', actor: 'assistant' })
const system = await memory.getSystemPrompt('You are a helpful assistant with durable user memory.')

const result = await generateText({
  model: google('gemini-2.5-flash'),
  system,
  prompt: 'Remember that I prefer quiet neighborhoods near good schools.',
  tools: memory.createAgenticToolset(),
  stopWhen: stepCountIs(5),
})

await memex.end()

Explicit adapter import

The named export is available if you prefer to import it directly.

import { createVercelAITools } from '@memexai/sdk/adapters/vercel-ai'
// or for direct mode:
import { createVercelAITools } from '@memexai/core/adapters/vercel-ai'

const agenticTools = createVercelAITools(memory)
const rawTools = createVercelAITools(memory, { mode: 'raw' })

Raw toolset

Pass { mode: 'raw' } to expose the full file-level tool set instead of the two agentic tools.

tools: memory.createRawToolset()
// memory_list, memory_read, memory_write, memory_patch, memory_smart_read

Use raw tools when your agent or workflow should control exactly what gets written.