RAG vs LLM Wiki vs Plain Text — A Decision Framework for Agent Long-Term Memory

Mon, 11 May 2026 00:00:00 +0000

Every Agent builder hits this question eventually: where do I store user data so the agent remembers it next session?

Three approaches dominate the landscape: RAG (vector retrieval), LLM Wiki (structured knowledge injection), and plain-text context memory (the CLAUDE.md / Cursor Rules pattern). Each has vocal advocates. But picking wrong is expensive — do RAG too light and it’s a noise generator; do plain text too heavy and it’s a token incinerator.

Agent Architecture on 卓琪的开发笔记

RAG vs LLM Wiki vs Plain Text — A Decision Framework for Agent Long-Term Memory