Ontology / custom entity types
What is an ontology in an AI memory system?
An ontology is the schema of a memory system — the definition of what kinds of things can exist in it and how they may relate. Custom entity types are the practical form: instead of storing everything as generic notes, you declare that your world contains clients, matters, or deployments, each with their own shape. It matters because the categories determine what can be retrieved later. A system that only knows about undifferentiated text cannot answer a question that depends on knowing a client is different from a colleague.
What this is called in Tempreon
Domains + Agents
Tempreon uses Domains to scope different areas of your work — personal, work, side projects — so the right memory is in the right place, and Agents to give each area a distinct way of operating.
See how it works