Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Cognis: Context-Aware Memory for Conversational AI Agents

About

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.

Parshva Daftari, Khush Patel, Shreyas Kapale, Jithin George, Siva Surendira• 2026

Related benchmarks

TaskDatasetResultRank
Long-context Memory EvaluationLongMemEval
Average Score92.4
103
Long-context Question AnsweringLoCoMo Single-Hop 2024
F1 Score48.66
12
Long-context Question AnsweringLoCoMo Multi-Hop 2024
F1 Score31.51
12
Long-context Question AnsweringLoCoMo Open-Domain 2024
F1 Score54.77
12
Long-context Question AnsweringLoCoMo Temporal 2024
F1 Score62.68
12
Showing 5 of 5 rows

Other info

Follow for update