SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges
SAG retrieves structured multi-hop evidence via event-entity hyperedges and query-time joins, without a maintained global knowledge graph.
Knowledge catalogue
SAG retrieves structured multi-hop evidence via event-entity hyperedges and query-time joins, without a maintained global knowledge graph.
Mem0 provides persistent user memory and agent memory; its vendor describes fact extraction, contradiction handling and relevant recall.
Natural language can act as an in-context control surface that streams rich, constrained UI and links users into deeper web views.
Zep offers a knowledge graph for persistent user memory and shared organisational context through MCP, according to Zep.
Karpathy’s pattern: LLMs compile raw sources into a persistent interlinked markdown wiki—entity/concept pages, index, log—rather than re-deriving answers from RAG on every query.
Mem0 documents a self-hosted agent-memory REST API with a pgvector vector store and Neo4j knowledge graph; local models are optional.
AD2-Bench diagnoses multimodal reasoning via a Chain of Evidence, showing failures from spatial ambiguity and semantic uncertainty in adverse urban scenes.
DoorDash and AWS describe a live Bedrock-backed voice agent for Dasher support, reporting hundreds of thousands of calls daily.