Skip to main content
GET
/
api
/
v2
/
memory
Get memories and buckets in a single request
curl --request GET \
  --url https://www.memoryplugin.com/api/v2/memory \
  --header 'Authorization: Bearer <token>'
{
  "memories": [
    "<string>"
  ],
  "buckets": [
    {
      "id": "<string>",
      "name": "<string>",
      "memoryCount": 123,
      "description": "<string>"
    }
  ]
}

Documentation Index

Fetch the complete documentation index at: https://help.memoryplugin.com/llms.txt

Use this file to discover all available pages before exploring further.

​
Image Memories

Search results may include image memories alongside text memories. Image memories are returned as objects with additional fields:
  • content_type: "image" — identifies this as an image memory
  • image_url — a signed URL to view the image (expires after 4 hours)
  • image_description — AI-generated description of the image content
Image memories are ranked by relevance alongside text memories using multimodal embeddings that enable cross-modal search (e.g., a text query can find visually relevant images).

​
Filtering by Content Type

Use the contentType query parameter to filter results: 
# Only text memories
curl "https://www.memoryplugin.com/api/v2/memory?query=architecture&contentType=text" \
  -H "Authorization: Bearer YOUR_API_KEY"

# Only image memories
curl "https://www.memoryplugin.com/api/v2/memory?query=diagram&contentType=image" \
  -H "Authorization: Bearer YOUR_API_KEY"

# All memories (default)
curl "https://www.memoryplugin.com/api/v2/memory?query=architecture" \
  -H "Authorization: Bearer YOUR_API_KEY"

​
Example Response with Image Memories

{
  "memories": [
    "User prefers dark mode in all applications",
    {
      "content_type": "image",
      "image_url": "https://memoryplugin.com/storage/v1/object/sign/memory-images/...",
      "image_description": "A whiteboard diagram showing the auth flow with three microservices connected via Redis pub/sub.",
      "metadata": {
        "createdAt": "2026-04-06T10:30:00Z",
        "bucketId": 65,
        "bucketName": "Work"
      }
    },
    "Meeting notes: decided to use PostgreSQL for the new service"
  ],
  "buckets": [
    { "id": 65, "name": "Work" },
    { "id": 66, "name": "Personal" }
  ]
}
Image URLs are temporary signed URLs that expire after 4 hours. If you need to access an image after the URL has expired, make another API request to get a fresh URL.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

​
bucketId
integer

Optional bucket ID to filter memories

​
count
integer
default:10

Number of memories to retrieve

​
all
boolean

Fetch all memories

​
latest
boolean

Fetch latest memories

​
query
string

Search query for memories

​
source
string

Client source identifier (e.g., 'chatgpt' for ChatGPT requests)

​
skip
integer
default:0

Number of memories to skip for pagination. Zero-indexed: skip=0 starts from first memory, skip=10 skips first 10 memories and starts from 11th. Used primarily with token limiting to load additional memories beyond the initial response.

Required range: x >= 0
​
includeIds
boolean
default:false

When true, text memories are returned as objects with id and text fields instead of plain strings. Useful for clients that need to reference specific memories for edit or delete operations.

​
contentType
enum<string>

Filter memories by content type. Use text for text-only memories, image for image-only memories. Omit to return all memories.

Available options:
text,
image

Response

Successful response with memories and buckets

​
memories
(string | object)[]

Array of memories. Text memories are returned as plain strings (or {id, text} objects when includeIds=true). Image memories are always returned as objects with content_type, image_url, and image_description fields.

Text memory (plain string format)

​
buckets
object[]