A developer compared Zep's temporal knowledge graph with nlqdb for agent memory, finding that Zep excels at recall and entity resolution but fails at aggregation queries like 'average per group', whil…
A developer who reverse-engineered Cognee, Graphiti, and Neo4j's agent-memory tools found they all rely on heavy knowledge-graph designs with ontologies, LLM extraction pipelines, and deduplication, w…
Zep, an agent memory platform, tracks provenance by recording the lineage of synthesized facts as a graph structure, enabling source-scoped retrieval, access control, and deletion propagation. The sys…
Four open-source projects—Graphiti, Hindsight, Mem0, and others—offer expanded memory capabilities for AI agents and large language models, using techniques like temporal knowledge graphs and multi-st…
Researchers introduced the Narrative World Model (NWM), a writer-memory system that uses a narratology-grounded typed temporal-state graph and query-conditioned hybrid retrieval to answer multi-hop qu…
Commonplace launches a self-hosted, privacy-tiered memory system for AI agents, using a two-tier Graphiti knowledge graph that runs entirely on local hardware by default, with a personal tier optional…
A developer compares four agent memory systems—Letta, Mem0, Graphiti, and Cognee—highlighting their approaches to knowledge graphs and long-term memory for AI agents. The analysis covers each system's…