memory.forget

coming soon

Forget one memory by id, remove a source document (and what was extracted from it), or forget everything matching a plain-language instruction ("everything about Project Titan"). Run the instruction with dry_run first to see what would go.

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_forget · unmatched results billed: no
Forgetting by id is the floor; a plain-language forget runs a small agent upstream and is priced as one operation.

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.forget",
    "input": {  },
    "routing": {"provider": "auto"}
  }'

Input schema

{
  "properties": {
    "document_id": {
      "description": "From memory.add: removes the document and its memories",
      "type": "string"
    },
    "dry_run": {
      "default": false,
      "description": "With query: preview the matches without forgetting anything",
      "type": "boolean"
    },
    "max_forget": {
      "default": 100,
      "description": "With query: cap on memories forgotten in one call, up to 500",
      "type": "integer"
    },
    "memory_id": {
      "description": "From memory.search, memory.profile or memory.list",
      "type": "string"
    },
    "namespace": {
      "description": "Same value you gave memory.add; omit for the workspace-wide memory",
      "type": "string"
    },
    "query": {
      "description": "Plain-language target, e.g. \"forget everything about Acme\u0027s old pricing\"",
      "type": "string"
    },
    "reason": {
      "description": "Stored on each forgotten memory",
      "type": "string"
    },
    "threshold": {
      "default": 0.5,
      "description": "With query: lower casts a wider net",
      "type": "number"
    }
  },
  "type": "object"
}

Normalized output fields

forgotten · dry_run · matched · summary · memories · memory_id · document_id