Every "AI memory agent" I looked at before starting this does the same trick: embed every message, dump it in a vector database, retrieve the top-k most similar chunks at query time. That's not memory. That's a search index.
Source: [Dev.to](https://dev.to/_boweii/i-built-an-ai-memory-agent-that-forgets-on-purpose-then-spent-two-days-proving-it-actually-works-2b87)