Optimize User Memories

Optimize all memories for a given user using the default summarize strategy. This operation combines all memories into a single comprehensive summary, achieving maximum token reduction while preserving all key information. To use a custom model, specify the model parameter in ‘provider:model_id’ format (e.g., ‘openai:gpt-4o-mini’, ‘anthropic:claude-3-5-sonnet-20241022’). If not specified, uses MemoryManager’s default model (gpt-4o). Set apply=false to preview optimization results without saving to database.

POST /optimize-memories

Optimize User Memories

cURL

curl --request POST \
  --url https://api.example.com/optimize-memories \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "user_id": "<string>",
  "model": "<string>",
  "apply": true
}
'

200

{
  "memories": [
    {
      "memory_id": "f9361a69-2997-40c7-ae4e-a5861d434047",
      "memory": "User has a 3-year-old golden retriever named Max who loves fetch and walks. Lives in San Francisco's Mission district, works as a product manager in tech. Enjoys hiking Bay Area trails, trying new restaurants (especially Japanese, Thai, Mexican), and learning piano for 1.5 years.",
      "topics": [
        "pets",
        "location",
        "work",
        "hobbies",
        "food_preferences"
      ],
      "user_id": "user2",
      "updated_at": "2025-11-18T10:30:00Z"
    }
  ],
  "memories_before": 4,
  "memories_after": 1,
  "tokens_before": 450,
  "tokens_after": 180,
  "tokens_saved": 270,
  "reduction_percentage": 60
}

Authorizations

Authorization · string · header · required

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

Query Parameters

db_id · string | null

Database ID to use for optimization

table · string | null

Table to use for optimization

Body

application/json

Schema for memory optimization request

user_id · string · required

User ID to optimize memories for

model · string | null

Model to use for optimization in format 'provider:model_id' (e.g., 'openai:gpt-4o-mini', 'anthropic:claude-3-5-sonnet-20241022', 'google:gemini-2.0-flash-exp'). If not specified, uses MemoryManager's default model (gpt-4o).

apply · boolean · default: true

If True, apply optimization changes to database. If False, return preview only without saving.

Response

200

application/json

Memories optimized successfully

Schema for memory optimization response

memories · UserMemorySchema · object[] · required

List of optimized memory objects

Show child attributes

memories_before · integer · required

Number of memories before optimization

Required range: x >= 0

memories_after · integer · required

Number of memories after optimization

Required range: x >= 0

tokens_before · integer · required

Token count before optimization

Required range: x >= 0

tokens_after · integer · required

Token count after optimization

Required range: x >= 0

tokens_saved · integer · required

Number of tokens saved through optimization

Required range: x >= 0

reduction_percentage · number · required

Percentage of token reduction achieved

Required range: 0 <= x <= 100