memory.search

coming soon

Ask the memory a question in plain language and get the memories that answer it, ranked by similarity, with the facts they superseded and the ones they relate to. Search memories (fast, conversational), the source documents (chunks with citations), or both.

Coming soon. No real adapter serves this capability yet. The sandbox returns clearly labeled mock data against the final schema, so you can integrate now and switch on real routing when the first provider goes live.

Providers

Provider	Status
Supermemory	adapter next

Billing

Unit: per_search · unmatched results billed: no

The exact quote is returned by /v1/inspect before every call and held with headroom (1.5x the quote) on execution. The quote is the price floor: if the provider's actual cost overruns it, the run bills at about 1.5x cost, never above the hold. The unused part of every hold is released.

Run it

curl https://api.routergrowth.com/v1/run \
  -H "Authorization: Bearer $ROUTERGROWTH_API_KEY" \
  -d '{
    "capability": "memory.search",
    "input": { "query": "..." },
    "routing": {"provider": "auto"}
  }'

Input schema

{
  "properties": {
    "include_related": {
      "default": false,
      "description": "Attach the memories each result extends or derives from",
      "type": "boolean"
    },
    "limit": {
      "default": 10,
      "description": "Up to 50",
      "type": "integer"
    },
    "mode": {
      "default": "memories",
      "description": "memories: extracted facts. documents: chunks of the sources. hybrid: both.",
      "enum": [
        "memories",
        "hybrid",
        "documents"
      ],
      "type": "string"
    },
    "namespace": {
      "description": "Same value you gave memory.add; omit for the workspace-wide memory",
      "type": "string"
    },
    "query": {
      "description": "e.g. \"what tools does Acme use\"",
      "type": "string"
    },
    "rerank": {
      "default": false,
      "description": "Rerank the results against the query (slower, more precise)",
      "type": "boolean"
    },
    "rewrite": {
      "default": false,
      "description": "Let Supermemory rewrite the query first (adds about 400 ms)",
      "type": "boolean"
    },
    "threshold": {
      "default": 0.6,
      "description": "0 returns the most, 1 only near-exact matches",
      "type": "number"
    }
  },
  "required": [
    "query"
  ],
  "type": "object"
}

Normalized output fields

results · count · timing_ms