Sign in

v1

latestOpenAPI 3.1.02026-07-26142186376.1 KB
Memory

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

Query parameters

db_idstring nullable

Database ID to use for optimization

Database ID to use for optimization

tablestring nullable

Table to use for optimization

Table to use for optimization

Request body

user_idstring required

User ID to optimize memories for

modelstring nullable

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).

applyboolean

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

Response

Memories optimized successfully

memories_beforeinteger required

Number of memories before optimization

memories_afterinteger required

Number of memories after optimization

tokens_beforeinteger required

Token count before optimization

tokens_afterinteger required

Token count after optimization

tokens_savedinteger required

Number of tokens saved through optimization

reduction_percentagenumber required

Percentage of token reduction achieved