Search memory
memory_searchSearch all remembered facts by content across every project scope. Use before assuming something is unknown; blends keyword and semantic matching to find entries even without shared terms.
Instructions
Search all remembered facts by content, across every project scope.
The default entry point. Use it before assuming something is not known: it searches EVERY scope at once, so there is no need to guess which project a fact was recorded under. Use memory_get instead when you already know the exact scope and name, memory_list to browse without a query, and memory_recent for what changed lately.
Two layers, blended by default:
Lexical (FTS5): multi-word queries first require ALL terms in one entry, then fall back to ANY term (ranked by how many match), so one non-verbatim word doesn't zero the result.
Semantic (if embeddings are present): vector nearest neighbours on a multilingual sentence model, which finds entries about the same idea even with no shared keywords.
Read-only. Archived entries are never returned. Returns a list of entries, best match first; an empty list when nothing matches or the query is invalid.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| debug | No | If true, return {results, mode, ...} instead of a plain list; `mode` tells which path matched (and / or_fallback / hybrid / vector / lexical). | |
| limit | No | Maximum number of results to return (default 20). Values are clamped to 1-200. | |
| query | Yes | Search terms or a natural-language question, in French or English. | |
| scope | No | Restrict to one project/topic scope (list them with memory_scopes). Omit to cover every scope. On a scope-locked connection (--scope), this argument is ignored and the connection's own scope is used. | |
| semantic | No | null = hybrid lexical + semantic (default), true = vector search only, false = lexical (FTS5) only. Semantic search needs the optional embeddings; without them the search is lexical. |