recall
Search persistent memory by semantic meaning to answer specific questions. Retrieves ranked memories using hybrid vector, text, and graph search with relevance scoring.
Instructions
Search persistent memory by meaning, returning the most relevant past memories ranked by semantic similarity. This is a read-only operation that runs a 4-way hybrid search (vector similarity, BM25 full-text, entity graph traversal, temporal proximity) and reranks results with a cross-encoder model. Use recall (not context) when you need to answer a specific question: "what language does the user prefer?", "how was auth implemented?", "what was decided about the database?". Do not use for broad session bootstrapping (use context instead). Returns up to limit memories with relevance scores (0-1). Costs 1 operation per call. If no memories match, returns an empty list, not an error.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Natural language search query. Semantic, not keyword-based: 'what programming language does the user prefer?' works better than 'language preference'. More specific queries return more relevant results. | |
| agent_id | No | Agent instance identifier. Must match the agent_id used when storing memories. Default: 'default'. | default |
| user_id | No | User identifier. When provided with scope 'user', also searches user-scoped memories shared by other agents. | |
| scope | No | Search scope. 'agent' (default): only this agent's memories. 'user': also includes memories shared to user scope. 'org': includes org-wide memories. Broader scope returns more results but may include less relevant memories. | |
| tags | No | Filter results to only memories with at least one matching tag. Omit to search all memories regardless of tags. | |
| limit | No | Maximum memories to return, 1-20. Default 5. Use higher values (10-20) for broad searches, lower (1-3) for targeted lookups. |