Create memory

Create a new memory with content analysis, embedding generation, and graph storage.

Note: As of the latest version, layerId is now required when creating memories.

Request

POST /v1/memories

Request Body

Field	Type	Required	Description
`content`	string	Yes	The text content of the memory
`layerId`	string	Yes	Layer identifier for organizing memories
`metadata`	object	Yes	Additional metadata (can be empty object)

Example Request

curl -X POST "https://api.memorylayer.dev/v1/memories" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "I prefer dark mode in my applications",
    "layerId": "REPLACE_THIS_LAYER_ID",
    "metadata": {
      "source": "preferences",
      "category": "ui"
    }
  }'

Response

Success Response (201)

{
  "success": true,
  "data": {
    "id": "REPLACE_THIS_MEMORY_ID",
    "layerId": "REPLACE_THIS_LAYER_ID",
    "content": "I prefer dark mode in my applications",
    "metadata": {
      "source": "preferences",
      "category": "ui",
      "analysis": {
        "sentiment": "neutral",
        "intent": "preference",
        "topics": ["ui", "preferences"],
        "summary": "User interface preference for dark mode",
        "entities_count": 2,
        "relationships_count": 1
      },
      "processing": {
        "analyzed_at": "2024-01-15T10:30:00Z",
        "embedding_model": "text-embedding-3-large",
        "embedding_dimensions": 1536
      }
    },
    "embedding": [0.123, -0.456, ...],
    "createdAt": "2024-01-15T10:30:00Z",
    "updatedAt": "2024-01-15T10:30:00Z"
  },
  "message": "Memory created successfully with analysis and graph storage"
}

Error Responses

Bad Request (400)

{
  "success": false,
  "message": "Invalid request data: layerId: Required"
}

Server Error (500)

{
  "success": false,
  "message": "OpenAI API key is required for memory processing"
}

{
  "success": false,
  "message": "Failed to generate embedding. Please check OpenAI API key and try again."
}

Processing Details

When you create a memory, the following processing occurs automatically:

Content Analysis: Extracts sentiment, intent, topics, entities, and relationships
Embedding Generation: Creates a 1536-dimensional vector using text-embedding-3-large
Graph Storage: Stores entities and relationships in the graph database
Enhanced Metadata: Adds analysis results and processing information

Examples

Minimal Request

curl -X POST "https://api.memorylayer.dev/v1/memories" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "Remember to buy groceries",
    "layerId": "REPLACE_THIS_LAYER_ID",
    "metadata": {}
  }'

With Layer and Metadata

curl -X POST "https://api.memorylayer.dev/v1/memories" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "Meeting with John at 3 PM tomorrow",
    "layerId": "REPLACE_THIS_LAYER_ID",
    "metadata": {
      "type": "appointment",
      "priority": "high",
      "participants": ["John"]
    }
  }'

JavaScript Example

const memory = {
  content: "I prefer dark mode in my applications",
  layerId: "REPLACE_THIS_LAYER_ID",
  metadata: {
    source: "preferences",
    category: "ui"
  }
};

const response = await fetch('https://api.memorylayer.dev/v1/memories', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify(memory)
});

const result = await response.json();
if (result.success) {
  console.log('Memory created:', result.data.id);
} else {
  console.error('Error:', result.message);
}

Python Example

import requests

memory_data = {
    "content": "Remember to call mom on Sunday",
    "layerId": "REPLACE_THIS_LAYER_ID",
    "metadata": {
        "type": "reminder",
        "priority": "medium"
    }
}

response = requests.post(
    "https://api.memorylayer.dev/v1/memories",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json=memory_data
)

if response.status_code == 201:
    memory = response.json()["data"]
    print(f"Created memory: {memory['id']}")
else:
    print(f"Error: {response.json()['message']}")

Create memory

On this page