06
Memory · state · RAG
Retrieval latency shapes the design
Reported This dimension was under-covered in final verification — treat as directional. Memory is optimized for fast reads (written once, read many). Latency by strategy:
memory retrieval latency · lower is faster
- Tiers: short-term/working (thread-scoped) + long-term (cross-session), plus episodic, semantic, procedural.
- ≥8 dedicated memory frameworks compete in 2026: Mem0, Letta, Zep/Graphiti, Cognee, SuperMemory, LangMem, LlamaIndex Memory, Hindsight.
- Index tradeoff at scale: HNSW = higher recall per latency but several× more memory; IVF = more memory-efficient at billions of vectors. Both tunable >95% recall.
- Big context ≠ no memory: windows reset per request and can't preserve cross-session identity or learned behavior.