Semantic Memory
An agent memory strategy based on vector retrieval that compresses conversations into embeddings stored in a vector database and recalls them by semantic similarity; it is essentially RAG.
Timeline (last 90 days)
The article categorizes Agent memory approaches into six types: Buffer, Window, Token, Summary, Long Term and Semantic.
Semantic Memory stores conversation content in a vector database via Embedding and recalls it by semantic similarity at retrieval time; its pipeline is the same as RAG, except that the knowledge source is historical conversation rather than external documents.
All Facts (2)
The article categorizes Agent memory approaches into six types: Buffer, Window, Token, Summary, Long Term and Semantic.
50%UnverifiedSemantic Memory stores conversation content in a vector database via Embedding and recalls it by semantic similarity at retrieval time; its pipeline is the same as RAG, except that the knowledge source is historical conversation rather than external documents.
50%