Waarom een AI-agent zonder geheugen een dure rekenmachine is. We bouwen een persistente memory

Product tech lead of Evolution AI Agents at Cloud.ru, Vladislav Yankovsky, talks about building persistent memory for AI agents. He notes that memory is not needed by itself, but as a consequence of functional requirements: if an agent can work without memory between sessions, then it is not needed. He gives an example of an agent for Grafana that does not need memory, and an L2 support agent for which it is critical. He distinguishes between context (in the model window) and memory (outside the model), as well as two dimensions of memory: lifespan (short-term, working, long-term) and content type (semantic, episodic, procedural). In 80% of cases, a combination of short-term and long-term semantic memory is sufficient. He describes memory levels: level 0 — simple storage of dialogue history, insufficient due to duplicates and lack of consolidation; level 1 — vector search using pgvector, Qdrant, Milvus, Pinecone; level 2 — structured memory with SQL and graphs, such as Graphiti. The key mistake is saving raw replies; the right approach is to extract facts and maintain a two-layer model with sources and extracted data.