Update Memory

Update an existing memory entry with new content, metadata, or category classification

PATCH /memories/{memory_id}

cURL

curl -X PATCH 'https://api.memchat.io/memories/mem_123abc' \
  -H 'X-API-Key: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "content": "Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.",
    "metadata": {
      "location": "Stanford Medical Center",
      "participants": ["Sarah Johnson", "Dr. Martinez"],
      "updated_at": "2024-01-15T16:30:00Z"
    },
    "category": "learning"
  }'

import requests

url = "https://api.memchat.io/memories/mem_123abc"
headers = {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "content": "Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.",
    "metadata": {
        "location": "Stanford Medical Center",
        "participants": ["Sarah Johnson", "Dr. Martinez"],
        "updated_at": "2024-01-15T16:30:00Z"
    },
    "category": "learning"
}

response = requests.patch(url, headers=headers, json=data)
memory = response.json()

const response = await fetch('https://api.memchat.io/memories/mem_123abc', {
  method: 'PATCH',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    content: 'Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.',
    metadata: {
      location: 'Stanford Medical Center',
      participants: ['Sarah Johnson', 'Dr. Martinez'],
      updated_at: '2024-01-15T16:30:00Z'
    },
    category: 'learning'
  }),
});

const memory = await response.json();

Response

{
  "memory_id": "mem_123abc",
  "content": "Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.",
  "category": "learning",
  "memory_type": "episodic",
  "importance": 0.85,
  "metadata": {
    "location": "Stanford Medical Center",
    "participants": ["Sarah Johnson", "Dr. Martinez"],
    "source": "conversation",
    "updated_at": "2024-01-15T16:30:00Z"
  },
  "embeddings": [0.123, -0.456, 0.789, ...],
  "created_at": "2024-01-15T14:30:00Z",
  "updated_at": "2024-01-15T16:30:00Z"
}

Updates a specific memory entry by ID. You can modify the memory content, metadata, category, or memory type.

cURL

curl -X PATCH 'https://api.memchat.io/memories/mem_123abc' \
  -H 'X-API-Key: YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "content": "Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.",
    "metadata": {
      "location": "Stanford Medical Center",
      "participants": ["Sarah Johnson", "Dr. Martinez"],
      "updated_at": "2024-01-15T16:30:00Z"
    },
    "category": "learning"
  }'

import requests

url = "https://api.memchat.io/memories/mem_123abc"
headers = {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "content": "Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.",
    "metadata": {
        "location": "Stanford Medical Center",
        "participants": ["Sarah Johnson", "Dr. Martinez"],
        "updated_at": "2024-01-15T16:30:00Z"
    },
    "category": "learning"
}

response = requests.patch(url, headers=headers, json=data)
memory = response.json()

const response = await fetch('https://api.memchat.io/memories/mem_123abc', {
  method: 'PATCH',
  headers: {
    'X-API-Key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    content: 'Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.',
    metadata: {
      location: 'Stanford Medical Center',
      participants: ['Sarah Johnson', 'Dr. Martinez'],
      updated_at: '2024-01-15T16:30:00Z'
    },
    category: 'learning'
  }),
});

const memory = await response.json();

Path Parameters

memory_id · string · required

The unique identifier of the memory to update

Request Body

content · string

Updated text content of the memory

metadata · object

Additional metadata to update for the memory

Show Metadata Properties

location · string

Location where the memory occurred

participants · array

List of people involved in the memory

tags · array

Custom tags for the memory

source · string

Source of the memory (e.g., “conversation”, “document”, “social_media”)

confidence · number

Confidence score between 0.0 and 1.0

category · string

Updated memory category. One of: identity, career, interests, relationships, health, finance, learning, travel, productivity, private

memory_type · string

Updated memory type: semantic or episodic

importance · number

Updated importance score between 0.0 and 1.0

Response

memory_id · string

Unique identifier of the updated memory

content · string

Updated text content of the memory

category · string

Updated memory category

memory_type · string

Updated memory type (semantic or episodic)

importance · number

Updated importance score

metadata · object

Updated memory metadata

embeddings · array

Vector embeddings for the updated content (if content was modified)

created_at · string

ISO 8601 timestamp when the memory was originally created

updated_at · string

ISO 8601 timestamp when the memory was last updated

Response

{
  "memory_id": "mem_123abc",
  "content": "Updated: Had an amazing conversation with Sarah about machine learning applications in healthcare. She mentioned some innovative approaches to medical imaging.",
  "category": "learning",
  "memory_type": "episodic",
  "importance": 0.85,
  "metadata": {
    "location": "Stanford Medical Center",
    "participants": ["Sarah Johnson", "Dr. Martinez"],
    "source": "conversation",
    "updated_at": "2024-01-15T16:30:00Z"
  },
  "embeddings": [0.123, -0.456, 0.789, ...],
  "created_at": "2024-01-15T14:30:00Z",
  "updated_at": "2024-01-15T16:30:00Z"
}

Error Responses

404 · object

Memory not found

{
  "error": "Memory not found",
  "code": "MEMORY_NOT_FOUND",
  "memory_id": "mem_123abc"
}

400 · object

Invalid request data

{
  "error": "Invalid category specified",
  "code": "INVALID_CATEGORY",
  "valid_categories": ["identity", "career", "interests", "relationships", "health", "finance", "learning", "travel", "productivity", "private"]
}

401 · object

Unauthorized access

{
  "error": "Invalid or expired API key",
  "code": "UNAUTHORIZED"
}

403 · object

Access denied - memory belongs to another user

{
  "error": "Access denied",
  "code": "FORBIDDEN"
}

Notes

• Only the fields provided in the request body will be updated
• If content is updated, new embeddings will be automatically generated
• Category changes may trigger re-classification and profile updates
• Memory type changes will affect how the memory is retrieved in searches
• All updates are versioned internally for audit purposes