ContextQMD
Back to Supermemory

Identifying Users

apps/docs/model-enhancement/identifying-users.mdx

latest2.7 KB
Original Source

You can enable built-in cross-conversational memory by sending supermemory a x-sm-user-id.

How supermemory Identifies Users and conversations

supermemory will find the user ID in the following places (in order of priority):

x-sm-user-id header

You can add a default header of x-sm-user-id with any client and model

user in body

For models that support the user parameter in the body, such as OpenAI, you can also attach it to the body.

userId in search params

You can also add ?userId=xyz in the URL search parameters, incase the models don't support it.

Conversation ID

If a conversation identifier is provided, You do not need to send the entire array of messages to supermemory.

typescript
// if you provide conversation ID, You do not need to send all the messages every single time. supermemory automatically backfills it.
const client = new OpenAI({
    baseURL:
"https://api.supermemory.ai/v3/https://api.openai.com/v1",
    defaultHeaders: {
        "x-supermemory-api-key":
            "SUPERMEMORY_API_KEY",
        "x-sm-user-id": `dhravya`,
        "x-sm-conversation-id": "conversation-id"
    },
})

const messages = [
{"role" : "user", "text": "SOme long thing"},
// .... 50 other messages
{"role" : "user", "text": "new message"},
]

const client.generateText(messages)

// Next time, you dont need to send more.
const messages2 = [{"role" : "user", "text": "What did we talk about in this conversation, and the one we did last year?"}]

const client.generateText(messages2)

Implementation Examples

Google Gemini

typescript
const ai = new GoogleGenAI({ apiKey: "YOUR_API_KEY" });

async function main() {
  const response = await ai.models.generateContent({
    model: "gemini-2.0-flash",
    contents: "Explain how AI works in a few words",
    config: {
      httpOptions: {
        headers: {
          'x-sm-user-id': "user_123"
        }
      }
    },
  });
  console.debug(response.text);
}

Anthropic

typescript
const anthropic = new Anthropic({
  apiKey: 'YOUR_API_KEY', // defaults to process.env["ANTHROPIC_API_KEY"]
});

async function main() {
  const msg = await anthropic.messages.create({
    model: "claude-sonnet-4-20250514",
    max_tokens: 1024,
    messages: [{ role: "user", content: "Hello, Claude" }],
  }, {
    // Using headers
    headers: {
      'x-sm-user-id': "user_123"
    }
  });

  console.debug(msg);
}

OpenAI

typescript
const openai = new OpenAI({
  apiKey: "YOUR_API_KEY"
});

async function main() {
  const completion = await openai.chat.completions.create({
    messages: [
      { role: "user", content: "Hello, Assistant" }
    ],
    model: "gpt-5",
    user: "user_123"
  });

  console.debug(completion.choices[0].message);
}