cuba-memorys
🧠 Persistent memory MCP for AI agents — Knowledge graph + Hebbian learning + Anti-hallucination. 12 tools, 1 dependency, zero manual setup.
Cuba-Memorys is a Model Context Protocol (MCP) server that gives AI coding assistants long-term persistent memory. It uses a knowledge graph, neuroscience-inspired algorithms like FSRS-6 adaptive decay, Hebbian learning, and dual-strength memory, along with anti-hallucination grounding. The latest version 2.0.0 is a complete Rust rewrite with 12 tools and sub-millisecond performance.
Features
Compatibility
Quick start
Use cases
Alternatives
Related searches
Comments
- Lane LeeMay 16, 2026
Knowledge graph memory with Hebbian learning for AI agents is a sophisticated approach.
- PParker GarciaMay 11, 2026
Associative memory that strengthens with use mirrors how memory works in practice.
- PPeyton MartinezApr 21, 2026
Good for agents doing long-term research or project work where associations matter.
- OOaklyn HarrisApr 2, 2026
Persistent across sessions, the knowledge graph grows more useful over time.