Skip to main content
POST
/
memory
/
ingest
curl -X POST https://api.60db.ai/memory/ingest \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "User prefers vegetarian food, lactose intolerant",
    "title": "Dietary preferences",
    "type": "user",
    "infer": true
  }'

{
  "success": true,
  "data": {
    "collection_id": "user_abc123",
    "collection_label": "Personal Memories",
    "memory_type": "user",
    "total_queued": 1,
    "results": [
      {
        "id": "mem_01HV8K2X3N4P5Q6R7S8T9U",
        "status": "pending",
        "message": "Memory queued for processing"
      }
    ]
  }
}
Store a new memory in your workspace. Memories are processed asynchronously — the response returns immediately with a pending memory ID that you can poll for status.

​
Request

​
Headers

​
Authorization
string
required
Bearer token with your API key
​
Content-Type
string
required
application/json

​
Body

​
text
string
required
The memory content to store. Max 100,000 characters.
​
title
string
Optional display title for the memory.
​
type
string
default:"user"
Memory type. One of: user, knowledge, hive.
  • user: Personal memory for the calling user
  • knowledge: Shared knowledge base entry (admin/owner only)
  • hive: Workspace-wide shared memory (admin/owner only)
​
collection
string
Collection ID to store the memory in. Defaults to the caller’s personal collection. For team collections, pass the collection_id returned from POST /memory/collections.
​
infer
boolean
default:"true"
If true, the memory service extracts structured facts and preferences via LLM inference.
​
metadata
object
Optional metadata to attach to the memory. Filterable at search time.

​
Response

​
success
boolean
True on success
​
data
object

​
Example

curl -X POST https://api.60db.ai/memory/ingest \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "User prefers vegetarian food, lactose intolerant",
    "title": "Dietary preferences",
    "type": "user",
    "infer": true
  }'

{
  "success": true,
  "data": {
    "collection_id": "user_abc123",
    "collection_label": "Personal Memories",
    "memory_type": "user",
    "total_queued": 1,
    "results": [
      {
        "id": "mem_01HV8K2X3N4P5Q6R7S8T9U",
        "status": "pending",
        "message": "Memory queued for processing"
      }
    ]
  }
}

​
Billing

This endpoint is billed at **0.0001per1,000characters∗∗of‘text‘.A500−charmemorycosts0.0001 per 1,000 characters** of `text`. A 500-char memory costs 0.00005; a 5,000-char memory costs $0.0005. The charge is deducted upfront from the workspace owner’s wallet, and automatically refunded if the request fails. Response headers — every successful request returns:
HeaderMeaning
x-credit-balanceYour wallet balance after this charge
x-credit-chargedAmount charged for this specific request
x-billing-txUUID of the audit row (for refunds/support)
See Pricing & Billing for the full rate card and refund policy.

​
Error responses

StatusCodeMeaning
400—Missing or invalid text field
402INSUFFICIENT_CREDITSWallet balance is lower than the ingest charge. Response body includes details.required, details.available, and details.shortfall.
403POLICY_DENYRole is not allowed to create memories (viewer)
503MEMORY_INFRA_NOT_READYThe memory layer is still being provisioned for this workspace (usually only on first use). Retry in ~10s.
503MEMORY_UNREACHABLEThe memory service is temporarily unavailable. Request is queued for retry and the charge is automatically refunded.

​
Checking status

Poll GET /memory/:id/status to check if a memory has been fully processed. Statuses: pending, processing, ready, failed.