Search Memories

Search for relevant memories within a memory space using hybrid retrieval (semantic + keyword + graph + temporal), RRF fusion, cross-encoder reranking, and recency/temporal boosting.

post/api/v1/search

Request body

querystring required

The search query text

space_idstring uuid required

The memory space to search within

limitinteger

Max number of results to return

recency_biasnumber nullable

Override recency weighting. 0.0 disables recency, higher values favor recent memories.

rerankboolean

Apply cross-encoder reranking. Disable for lower latency.

graphboolean

Include graph traversal signal. Disable for semantic + keyword only.

diversifyboolean

Apply MMR diversity post-rerank. Enable for broad/summarization intents.

include_sourceboolean

Include original source text in results.

recall_idstring uuid

Optional stable id for one logical recall. Retries of the same logical search should reuse the same value: the server then reuses a single concurrency slot instead of counting each retry as a new concurrent search. Omit it and behavior is unchanged. Generate a fresh id per distinct search — reusing one id across genuinely different searches makes them share a slot.

Response

Ranked memory candidates

querystring required