equilibrium
Drift correction. As a session runs long, replies can start to loop, flatten, or circle whatever the last stretch was about. This brings the range back. Use it when that happens. For a specific fact use deep_recall or gather, which stay closer to the query. Returns up to 12.
wide = mem.engram("equilibrium", "how have things been lately?", user_id="alice")Response
{ "engram": "equilibrium", "hops": 3, "count": 12,
"memories": [ ... ],
"usage": { "input_tokens": 300, "output_tokens": 293 } }Metered by tokens - every call returns
usage (input + output), counted by the same tokenizer as the rest of the API; no hidden per-engram fee. Need several at once? Call them concurrently - each engram is an independent request.