Add memory

Store memories from conversation messages. Automatically extracts facts and handles deduplication.

Use tag_1 through tag_12 for filtering - these are generic indexed fields you can use for any purpose:

• Legal app: tag_1=client_id, tag_2=matter_id
• Healthcare: tag_1=patient_id, tag_2=encounter_id
• E-commerce: tag_1=customer_id, tag_2=order_id

POST /memory/v1

cURL

cURL

curl -X POST "https://api.case.dev/memory/v1" \ -H "Authorization: Bearer $CASEDEV_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [ { "role": "user", "content": "<string>" } ] }'

200

{
  "results": [
    {
      "id": "<string>",
      "memory": "<string>"
    }
  ]
}

Authorizations

Authorization · string · header · required

API key starting with sk_case_

Body

application/json

messages · object[] · required

Conversation messages to extract memories from

Show child attributes

tag_1 · string

Generic indexed filter field 1 (you decide what it means)

tag_2 · string

Generic indexed filter field 2

tag_3 · string

Generic indexed filter field 3

tag_4 · string

Generic indexed filter field 4

tag_5 · string

Generic indexed filter field 5

tag_6 · string

Generic indexed filter field 6

tag_7 · string

Generic indexed filter field 7

tag_8 · string

Generic indexed filter field 8

tag_9 · string

Generic indexed filter field 9

tag_10 · string

Generic indexed filter field 10

tag_11 · string

Generic indexed filter field 11

tag_12 · string

Generic indexed filter field 12

category · string

Custom category (e.g., "fact", "preference", "deadline")

metadata · object

Additional metadata (not indexed)

infer · boolean · default: true

Whether to extract facts from messages (default: true)

extraction_prompt · string

Optional custom prompt for fact extraction

Response

200

application/json

Memories added successfully

results · object[]

Show child attributes