Nexo

This implements a multi-layer memory system for AI agents based on the Atkinson-Shiffrin model, combining sensory buffers, short-term working memory, and long-term storage. It exposes over 100 tools that let you store and retrieve information using RAG and knowledge graph structures, giving your agent persistent context across sessions. Reach for this when you need more than conversation history, like building an assistant that remembers user preferences, maintains a knowledge base, or connects facts across multiple interactions. The cognitive psychology foundation means memory gets encoded, consolidated, and retrieved similar to human cognition rather than just dumping everything into a vector database.