Mem0 Provider for Vercel AI SDK

What it does

When your agent uses it

• Giving a Vercel AI SDK chatbot memory across conversations
• Wrapping generateText or streamText calls with automatic memory retrieval
• Controlling exactly when memories are retrieved and stored
• Adding memory-augmented AI to a Next.js app

Example prompts

• “Add Mem0 memory to my Next.js chat route that uses streamText.”
• “Use retrieveMemories and addMemories so I control when memories are saved for each user.”
• “Switch the Mem0 provider in this app from OpenAI to Anthropic.”

Requirements

• Node.js 18 or newer
• The @mem0/vercel-ai-provider and ai npm packages
• MEM0_API_KEY and an API key for the LLM provider
• Compatibility (from SKILL.md): Node.js 18+, npm install @mem0/vercel-ai-provider, Vercel AI SDK v6 (ai package ^6), MEM0_API_KEY + LLM provider API key

Workflow steps

2 steps, taken from the step headings in SKILL.md.

1. 1Install
2. 2Set up environment variables

What it can do on your machine

Read from SKILL.md and the folder at commit b7ad69a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.mem0.ai

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • OPENAI_API_KEY
  • ANTHROPIC_API_KEY
  • MEM0_API_KEY
  • GOOGLE_GENERATIVE_AI_API_KEY
  • GROQ_API_KEY
  • COHERE_API_KEY
  • GOOGLE_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Node.js 18+, npm install @mem0/vercel-ai-provider, Vercel AI SDK v6 (ai package ^6), MEM0_API_KEY + LLM provider API key

  From compatibility in the SKILL.md frontmatter.

Context cost

Mem0 Provider for Vercel AI SDK loads about 2.3k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 134 tokens; SKILL.md has 625 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~134

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~10k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mem0ai/mem0 at commit b7ad69a, republished under its Apache-2.0 licence (© mem0ai). 625 words, ~2,295 tokens.

name

mem0-vercel-ai-sdk

description

Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also triggers for Next.js apps needing memory-augmented AI. DO NOT TRIGGER when: user asks about direct Python/TS SDK calls without Vercel (use mem0 skill), or CLI terminal commands (use mem0-cli skill).

compatibility

Node.js 18+, npm install @mem0/vercel-ai-provider, Vercel AI SDK v6 (ai package ^6), MEM0_API_KEY + LLM provider API key

license

Apache-2.0

metadata.author

mem0ai

metadata.version

2.0.0

metadata.category

ai-memory

metadata.tags

vercel, ai-sdk, memory, nextjs, typescript, provider

metadata.mem0_tested_versions

@mem0/vercel-ai-provider (npm) >=3.0.0,<4.0.0; ai (npm) >=6.0.0,<7.0.0; mem0ai (npm) >=3.0.0,<4.0.0

npm install @mem0/vercel-ai-provider ai@^6

export MEM0_API_KEY="m0-xxx"
export OPENAI_API_KEY="sk-xxx"   # or ANTHROPIC_API_KEY, GOOGLE_API_KEY, etc.

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

const mem0 = createMem0();
const { text } = await generateText({
  model: mem0("gpt-5-mini", { user_id: "alice" }),
  prompt: "Recommend a restaurant",
});

const { text, sources } = await generateText({
  model: mem0("gpt-5-mini", { user_id: "alice" }),
  prompt: "Recommend a restaurant",
});

console.log(sources.find((s) => s.title === "Mem0 Memories")?.providerMetadata?.mem0);

import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";
import { retrieveMemories, addMemories } from "@mem0/vercel-ai-provider";

const prompt = "Recommend a restaurant";

// Retrieve memories -- returns a formatted system prompt string
const memories = await retrieveMemories(prompt, {
  user_id: "alice",
  mem0ApiKey: "m0-xxx",
});

// Generate using any provider with injected memories
const { text } = await generateText({
  model: openai("gpt-5-mini"),
  prompt,
  system: memories,
});

// Optionally store the conversation back
await addMemories(
  [
    { role: "user", content: [{ type: "text", text: prompt }] },
    { role: "assistant", content: [{ type: "text", text }] },
  ],
  { user_id: "alice", mem0ApiKey: "m0-xxx" }
);

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

const mem0 = createMem0();
const result = streamText({
  model: mem0("gpt-5-mini", { user_id: "alice" }),
  prompt: "What should I cook for dinner?",
});

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

const mem0 = createMem0({ provider: "anthropic" });
const { text } = await generateText({
  model: mem0("claude-sonnet-4-20250514", { user_id: "alice" }),
  prompt: "Hello!",
});

User prompt
  --> processMemories: addMemories (POST /v3/memories/add/, awaited)
  --> processMemories: getMemories (POST /v3/memories/search/)
  --> memories (if any) injected as system message at start of prompt
  --> underlying LLM generates response (doGenerate or doStream)
  --> response returned to caller (doGenerate also attaches a "Mem0 Memories" source)

User controls each step:
  1. retrieveMemories / getMemories / searchMemories -> fetch memories
  2. inject into system prompt manually
  3. call generateText / streamText with any provider
  4. addMemories -> store new conversation to Mem0

© mem0ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (references) in skills/mem0-vercel-ai-sdk of mem0ai/mem0.

• SKILL.md
• LICENSE
• README.md
• references/memory-utilities.md
• references/provider-api.md
• references/usage-patterns.md

Open the folder on GitHubat commit b7ad69a