Skip to main content
The Jean Memory Node.js SDK is a headless library for integrating our Context API into your backend services.

​
Installation

npm install @jeanmemory/node

​
Usage: Context-Aware API Route

Create a secure bridge between your frontend and your LLM.
1

Extract User Token

Pull the userToken from the request body. This proves the user’s identity (handled by React SDK).
2

Fetch Context

Call jean.getContext() to get relevant memories for the user’s current message.
3

Stream Response

Inject the context into your system prompt and stream the LLM response back to the client.

​
Next.js Example (App Router)

import { JeanClient } from '@jeanmemory/node';
import OpenAI from 'openai';
import { OpenAIStream, StreamingTextResponse } from 'ai';

const jean = new JeanClient({ apiKey: process.env.JEAN_API_KEY });
const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

export const runtime = 'edge';

export async function POST(req: Request) {
  // 1. Get data
  const { messages, userToken } = await req.json();
  const lastMessage = messages[messages.length - 1].content;

  // 2. Get Context
  const context = await jean.getContext({
    user_token: userToken,
    message: lastMessage,
    speed: "balanced"
  });

  // 3. Create Prompt
  const prompt = `
    Context: ${context.text}
    Question: ${lastMessage}
  `;
  
  // 4. Stream Response
  const response = await openai.chat.completions.create({
    model: 'gpt-4-turbo',
    stream: true,
    messages: [{ role: "user", content: prompt }],
  });

  const stream = OpenAIStream(response);
  return new StreamingTextResponse(stream);
}

​
Configuration

// "fast", "balanced", "comprehensive"
await jean.getContext({
  user_token: token,
  message: msg,
  speed: "fast"
});

​
Direct Tool Access

For advanced deterministic control, access the tools namespace directly. 
// Add Memory
await jean.tools.add_memory({ 
  user_token: token, 
  content: "Project deadline is Friday" 
});

// Search Memory
const results = await jean.tools.search_memory({ 
  user_token: token, 
  query: "deadlines" 
});