Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

mnemo.recall

Retrieve memories using semantic search, full-text search, exact filters, graph traversal, or hybrid retrieval.

Input Schema

FieldTypeRequiredDescription
querystringyesSearch query
agent_idstringnoFilter by agent (uses server default)
limitnumbernoMax results (default 10)
memory_typestringnoFilter by single type
memory_typesstring[]noFilter by multiple types
scopestringnoFilter by scope
min_importancenumbernoMinimum importance threshold
tagsstring[]noFilter by tags (any match)
org_idstringnoFilter by organization
strategystringnovector, bm25, exact, graph, hybrid (default: hybrid)
temporal_rangeobjectno{ after: string, before: string } ISO timestamps

Strategies

  • vector: Cosine similarity via USearch/pgvector
  • bm25: Full-text search via Tantivy
  • exact: Filter-only (no embeddings needed)
  • graph: Vector seeds + 2-hop graph expansion with RRF
  • hybrid (default): Vector + BM25 + recency + graph fused via RRF

Response

FieldTypeDescription
memoriesarrayMatching memories with scores
totalnumberTotal count of results

Each memory includes: id, agent_id, content, memory_type, scope, importance, tags, score, created_at, updated_at.

Example

{
  "query": "user preferences",
  "strategy": "hybrid",
  "limit": 5,
  "min_importance": 0.3
}