Mem0 | AI SDK

The Mem0 Provider is a library developed by Mem0 to integrate with the AI SDK. This library brings enhanced AI interaction capabilities to your applications by introducing persistent memory functionality.

🎉 Exciting news! Mem0 AI SDK now supports Tools Call.

Setup

The Mem0 provider is available in the @mem0/vercel-ai-provider module. You can install it with:

$ pnpm add @mem0/vercel-ai-provider

$ npm install @mem0/vercel-ai-provider

$ yarn add @mem0/vercel-ai-provider

$ bun add @mem0/vercel-ai-provider

Provider Instance

First, get your Mem0 API Key from the Mem0 Dashboard.

Then initialize the Mem0 Client in your application:

import { createMem0 } from '@mem0/vercel-ai-provider';

const mem0 = createMem0({
  provider: 'openai',
  mem0ApiKey: 'm0-xxx',
  apiKey: 'provider-api-key',
  config: {
    // Configure the LLM Provider here
  },
  // Optional Mem0 Global Config
  mem0Config: {
    user_id: 'mem0-user-id',
    enable_graph: true,
  },
});

The openai provider is set as default. Consider using MEM0_API_KEY and OPENAI_API_KEY as environment variables for security.

The mem0Config is optional. It is used to set the global config for the Mem0 Client (eg. user_id, agent_id, app_id, run_id, org_id, project_id etc).

Add Memories to Enhance Context:

import { LanguageModelV2Prompt } from '@ai-sdk/provider';
import { addMemories } from '@mem0/vercel-ai-provider';

const messages: LanguageModelV2Prompt = [
  { role: 'user', content: [{ type: 'text', text: 'I love red cars.' }] },
];

await addMemories(messages, { user_id: 'borat' });

Features

Adding and Retrieving Memories

retrieveMemories(): Retrieves memory context for prompts.
getMemories(): Get memories from your profile in array format.
addMemories(): Adds user memories to enhance contextual responses.

await addMemories(messages, {
  user_id: 'borat',
  mem0ApiKey: 'm0-xxx',
});
await retrieveMemories(prompt, {
  user_id: 'borat',
  mem0ApiKey: 'm0-xxx',
});
await getMemories(prompt, {
  user_id: 'borat',
  mem0ApiKey: 'm0-xxx',
});

For standalone features, such as addMemories, retrieveMemories, and getMemories, you must either set MEM0_API_KEY as an environment variable or pass it directly in the function call.

getMemories will return raw memories in the form of an array of objects, while retrieveMemories will return a response in string format with a system prompt ingested with the retrieved memories.

Generate Text with Memory Context

You can use language models from OpenAI, Anthropic, Cohere, and Groq to generate text with the generateText function:

import { generateText } from 'ai';
import { createMem0 } from '@mem0/vercel-ai-provider';

const mem0 = createMem0();

const { text } = await generateText({
  model: mem0('gpt-4.1', { user_id: 'borat' }),
  prompt: 'Suggest me a good car to buy!',
});

Structured Message Format with Memory

import { generateText } from 'ai';
import { createMem0 } from '@mem0/vercel-ai-provider';

const mem0 = createMem0();

const { text } = await generateText({
  model: mem0('gpt-4.1', { user_id: 'borat' }),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'Suggest me a good car to buy.' },
        { type: 'text', text: 'Why is it better than the other cars for me?' },
      ],
    },
  ],
});

Streaming Responses with Memory Context

import { streamText } from 'ai';
import { createMem0 } from '@mem0/vercel-ai-provider';

const mem0 = createMem0();

const { textStream } = streamText({
  model: mem0('gpt-4.1', {
    user_id: 'borat',
  }),
  prompt:
    'Suggest me a good car to buy! Why is it better than the other cars for me? Give options for every price range.',
});

for await (const textPart of textStream) {
  process.stdout.write(textPart);
}

Generate Responses with Tools Call

import { generateText } from 'ai';
import { createMem0 } from '@mem0/vercel-ai-provider';
import { z } from 'zod';

const mem0 = createMem0({
  provider: 'anthropic',
  apiKey: 'anthropic-api-key',
  mem0Config: {
    // Global User ID
    user_id: 'borat',
  },
});

const prompt = 'What the temperature in the city that I live in?';

const result = await generateText({
  model: mem0('claude-3-5-sonnet-20240620'),
  tools: {
    weather: tool({
      description: 'Get the weather in a location',
      parameters: z.object({
        location: z.string().describe('The location to get the weather for'),
      }),
      execute: async ({ location }) => ({
        location,
        temperature: 72 + Math.floor(Math.random() * 21) - 10,
      }),
    }),
  },
  prompt: prompt,
});

console.log(result);

Get sources from memory

const { text, sources } = await generateText({
  model: mem0('gpt-4.1'),
  prompt: 'Suggest me a good car to buy!',
});

console.log(sources);

This same functionality is available in the streamText function.

Supported LLM Providers

The Mem0 provider supports the following LLM providers:

Provider	Configuration Value
OpenAI	`openai`
Anthropic	`anthropic`
Google	`google`
Groq	`groq`
Cohere	`cohere`

Best Practices

User Identification: Use a unique user_id for consistent memory retrieval.
Memory Cleanup: Regularly clean up unused memory data.

We also have support for agent_id, app_id, and run_id. Refer Docs.

Help

For more details on Vercel AI SDK, visit the Vercel AI SDK documentation.
For Mem0 documentation, refer to the Mem0 Platform.
If you need further assistance, please feel free to reach out to us through following methods: