Local Memory

Provides local memory storage and retrieval for AI agents using vector embeddings generated by Ollama models. Stores memories as vectors in a Zvec database with metadata including workspace keys, memory types (decisions, preferences, facts, etc.), importance scores, and timestamps. Features semantic search, memory superseding for updates, workspace isolation, and automatic relevance scoring based on embedding similarity and importance weights. Designed for agents that need persistent memory across conversations without relying on external cloud services.