Cuba Memorys

A heavyweight persistent memory layer that goes far beyond key-value storage. Built on PostgreSQL with 25 tools spanning entity management, knowledge graphs, episodic memory, and hybrid search combining BM25, vector embeddings, and MMR diversification. Implements neuroscience-inspired decay curves (Hebbian plasticity, BCM metaplasticity), LLM-powered contradiction detection via Claude CLI, and Leiden community detection for graph analytics. Ships with CFR-21 audit trails, project-scoped isolation, git-friendly JSON exports, and conformal prediction for out-of-distribution abstention. Reach for this when you need AI agents to remember context across sessions with mathematical rigor, not just append to a log file. Written in Rust with zero clippy warnings and 97 tests covering the cognitive algorithms.