> ## Documentation Index
> Fetch the complete documentation index at: https://docs.memorylake.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Add Memory

> Submit a conversation to extract and store memories

```
POST /openapi/memorylake/api/v2/projects/{id}/memories
```

Submits a user–assistant conversation to the project. Structured memories are automatically extracted from the messages and stored asynchronously. The response includes an event ID that can be used to track processing progress.

<Note>
  **Permission required:** [`project:mem_add`](/features/team-collaboration/permission-reference#add-a-memory-via-api-api-only) · `instance`
</Note>

### Path Parameters

<ParamField path="id" type="string" required>
  Project ID (format: `proj-{uuid}`)
</ParamField>

### Request Body

<ParamField body="messages" type="array" required>
  Array of message objects representing the conversation. Each message contains a `role` (`user` or `assistant`) and `content`.
</ParamField>

<ParamField body="user_id" type="string">
  Unique identifier of the user associated with this memory
</ParamField>

<ParamField body="chat_session_id" type="string">
  Unique identifier of the chat session
</ParamField>

<ParamField body="infer" type="boolean" default="true">
  Whether to infer memories from messages, or store messages directly. Defaults to `true` (infer mode).
</ParamField>

<ParamField body="metadata" type="object">
  Additional arbitrary metadata key-value pairs
</ParamField>

<RequestExample>
  ```bash cURL theme={null}
  curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v2/projects/proj-a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6/memories' \
    -H 'Authorization: Bearer sk_xxxxxx' \
    -H 'Content-Type: application/json' \
    -d '{
      "messages": [
        {"role": "user", "content": "What restaurants do you recommend in Hangzhou?"},
        {"role": "assistant", "content": "I recommend trying Grandma'\''s Kitchen for Hangzhou cuisine and Green Tea Restaurant for a modern take on local dishes."}
      ],
      "user_id": "user-abc123",
      "chat_session_id": "session-abc123",
      "infer": true
    }'
  ```
</RequestExample>

### Response

<ResponseField name="data" type="object">
  <Expandable title="Add memory result">
    <ResponseField name="results" type="array">
      Array of async processing results

      <Expandable title="Result item">
        <ResponseField name="message" type="string">Status message</ResponseField>
        <ResponseField name="status" type="string">Processing status (e.g. `PENDING`)</ResponseField>
        <ResponseField name="event_id" type="string">Event ID for tracking processing progress</ResponseField>
      </Expandable>
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseExample>
  ```json Success (200) theme={null}
  {
    "success": true,
    "message": "Operation completed successfully",
    "data": {
      "results": [
        {
          "message": "Memory processing has been queued for background execution",
          "status": "PENDING",
          "event_id": "97ba056d-df1b-4236-886a-4db825f29227"
        }
      ]
    }
  }
  ```
</ResponseExample>