Agent memory API: a ready-to-paste context block for a subject
memory.profile
coming soonEverything the memory knows about a namespace, pre-computed by learner-1: the permanent facts, the recent ones, and a ready-to-paste context block for your prompt. Add a query to get the memories relevant to what you are about to do in the same call.
Coming soon. No real adapter serves this capability yet, so a run on a live key is refused and nothing is charged. The schema below is final: build against it now and it runs the day the first provider goes live.
Providers
| Provider | Status |
|---|---|
 Supermemory |
adapter next |
Billing
Unit: per_profile · unmatched results billed: no
The exact quote is returned by /v1/inspect before every call and held with headroom on execution. The quote is the price floor: if the provider's actual cost overruns it, the run bills the overrun at the same rate, 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.profile", "input": { }, "routing": {"provider": "auto"} }'
Input schema
{
"properties": {
"limit": {
"default": 10,
"description": "With query: up to 50 results",
"type": "integer"
},
"namespace": {
"description": "Same value you gave memory.add; omit for the workspace-wide memory",
"type": "string"
},
"query": {
"description": "Optional: also return the memories relevant to this, e.g. \"drafting a follow-up about pricing\"",
"type": "string"
},
"sections": {
"description": "Subset of the profile to return; omit for all",
"items": {
"enum": [
"static",
"dynamic",
"buckets"
],
"type": "string"
},
"type": "array"
},
"threshold": {
"default": 0.6,
"type": "number"
}
},
"type": "object"
}
Normalized output fields
static · dynamic · buckets · results · context · count