recall
Search persistent memory by keywords to find specific project knowledge; filter by tags, scope, or time and return ranked results with scores.
Instructions
SEARCH memory by keywords. Use to find a SPECIFIC piece of knowledge, e.g. 'API convention' or 'license decision'. Returns ranked results with scores. Default view is compact: per item key, tags, score and the first ~300 chars of content (a trailing … marks a cut; timestamps, scope and bookkeeping fields are omitted). For the whole text of one entry call get_memory(key); full=true returns every item uncut with all stored fields (created_at included). Below the relevance threshold, returns an empty list with an explanation instead of weak matches. For loading ALL project knowledge at session start, use get_project_knowledge instead. Set include_archived=true to retrieve archived memories.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| full | No | Return every item in full, with all stored fields and uncut content (default false: compact view, content cut at ~300 chars and marked with a trailing `…`, bookkeeping fields such as agent_id, workspace_id, simhash and decay scores are left out). Prefer get_memory(key) to read one cut entry in full; full=true re-fetches the whole page uncut. | |
| tags | No | AND-filter: memory must contain ALL listed tags. | |
| limit | No | Max results (1–50). Omitted compact requests use 5; full=true or an explicit profile keeps the previous default 10. Existing profile presets still apply when limit is omitted (multi-session uses 20, including automatic classification). Explicit limit wins. This is a hard bound: the response never contains more than limit items. When knowledge-graph boost is enabled, a share of the page (limit/4, at least 1 when limit>=2) may be filled with graph-expanded neighbours, marked graph_boost=true and provenance=via:graph — they take the tail slots instead of being added on top. Rows that fail scope/tags are dropped, never returned unmarked, whether they arrived by retrieval, by pinning, or by graph expansion. | |
| query | Yes | Full-text search query. | |
| scope | No | Filter by scope: workspace, project, agent, or all (default). | |
| since | No | Return memories created at or after this RFC3339 timestamp. | |
| until | No | Return memories created at or before this RFC3339 timestamp. | |
| offset | No | Pagination offset (default 0). | |
| order_by | No | Sort order: created_at:desc (default), created_at:asc, relevance:desc, decayed_relevance:desc. | |
| tags_any | No | OR-filter: memory must contain AT LEAST ONE of these tags. | |
| created_by | No | Filter by agent ID (UUID). | |
| project_id | No | Filter to a specific project. | |
| relevance_min | No | Minimum relevance score (0-1). | |
| min_importance | No | Minimum importance_score threshold (0-1, default 0.3 — matches the lowest score the server assigns, kind:session-checkpoint, so prior-session hand-offs are returned without an override). Raise it to exclude low-value entries; pass 0 to disable filtering entirely. | |
| recall_profile | No | Override automatic query classification. Existing preset values are preserved; explicit limit takes precedence. | |
| include_expired | No | Include expired memories (default false). | |
| include_archived | No | Include archived memories in results (default false). | |
| apply_recency_decay | No | Sort by relevance * 0.95^days_since_created. |