{children}

; Everything in this section is one of four steps. Same loop whether you're building personal memory, RAG over docs, or both on the same `containerTag`. Raw input becomes **memories** (the knowledge graph) and/or indexed **document chunks** (for RAG) automatically — see [how it works](/docs/concepts/how-it-works). You don't choose one or the other; both build from the same write. Retrieval gives you three ways to read that same pool back — see [Memory vs RAG](/docs/concepts/memory-vs-rag) if you're not sure which one fits. ## Where next Walk the whole loop end to end with one working example. What happens between `add()` and a memory showing up in search. The isolation boundary every ingest and retrieve call is scoped to. When to reach for search, profiles, or both. Run standardized, reproducible evals against Supermemory and other providers — including your own.

{title}