Cognis: Context-Aware Memory for Conversational AI Agents
This addresses the limitation of conversational AI agents resetting conversations each session, enabling personalization over time.
The authors tackled the problem of LLM agents lacking persistent memory by developing Cognis, a unified memory architecture that achieved state-of-the-art performance on two independent benchmarks (LoCoMo and LongMemEval) across eight answer generation models.
LLM agents lack persistent memory, causing conversations to reset each session and preventing personalization over time. We present Lyzr Cognis, a unified memory architecture for conversational AI agents that addresses this limitation through a multi-stage retrieval pipeline. Cognis combines a dual-store backend pairing OpenSearch BM25 keyword matching with Matryoshka vector similarity search, fused via Reciprocal Rank Fusion. Its context-aware ingestion pipeline retrieves existing memories before extraction, enabling intelligent version tracking that preserves full memory history while keeping the store consistent. Temporal boosting enhances time-sensitive queries, and a BGE-2 cross-encoder reranker refines final result quality. We evaluate Cognis on two independent benchmarks -- LoCoMo and LongMemEval -- across eight answer generation models, demonstrating state-of-the-art performance on both. The system is open-source and deployed in production serving conversational AI applications.