Semantic memory
Semantic memory is compact stored information about important facts, preferences, or events that can be retrieved later because of meaning rather than raw message order.
The entries below are preserved in their original source language to avoid unreviewed machine translation.
In AI roleplay, semantic memory is useful when the app needs to preserve names, promises, relationship changes, locations, secrets, and unresolved plot points without replaying the whole transcript.
Plain-language meaning
It is memory as meaning, not memory as every sentence. The app tries to save what matters for the next scene.
Semantic-memory terms connect privacy, memory quality, long roleplay, and paid-tier decisions.
OnlyKin should explain semantic memory as compact continuity, while being clear that memory also affects privacy expectations.