mnemostack_search
Search indexed memories with hybrid recall, combining BM25, semantic, graph, and temporal retrievers for ranked results.
Instructions
Search indexed memories with hybrid recall.
Read-only, no side effects, no authentication required. Use this when you need raw memory matches rather than a synthesized answer. Returns a JSON object with ok, query, count, results, tokens_estimate (estimated total text tokens of the results), and degraded (which components fell back while serving the call; empty when healthy). Results are ranked by reciprocal rank fusion of BM25, semantic, graph, and temporal retrievers when configured; each result includes id, text, score, sources, and payload. Stale facts (invalidated_at set) are hidden by default; use include_invalidated or as_of to see them.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| as_of | No | Point-in-time recall (ISO-8601): return facts valid at this world-time instant, ignoring later invalidation. | |
| limit | No | Maximum number of results to return (default 10) | |
| query | Yes | Natural language question or keyword to search memories for | |
| filters | No | Payload filters applied inside every retriever: exact match ({"tenant": "a"}) or gte/lte range ({"timestamp": {"gte": "2026-01-01"}}). Results never include points outside the filtered scope. | |
| token_budget | No | Hard cap on the total (estimated) text tokens of the returned results; the final ranking is cut to the prefix that fits. Unset uses the server-wide default, if any. | |
| include_trace | No | Include the per-retriever recall trace (debug; verbose) | |
| include_invalidated | No | Include facts marked stale. Default false: memories with an invalidated_at marker are hidden from recall. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||