Hot Memory Mcp

This is a persistent memory layer for Claude that optimizes for access patterns. It maintains a hot cache of frequently used memories that get auto-injected into context before each request (zero latency), backed by a semantic search layer for everything else. The system self-organizes through promotion and demotion: memories used 3+ times move into the hot tier, unused ones decay after 14 days. It isolates memories per git repository, builds a knowledge graph between related concepts, and can bootstrap from your project docs. Exposes tools for remember, recall, promote/demote, and link_memories operations. Ships with a dashboard at localhost:8765 and works with local SQLite and embeddings. Reach for this when you're tired of re-explaining your architecture every session and want Claude to learn what matters in your codebase.