V3 Memory Unification

What problem does it solve? Fragmented memory backends (SQLite, Markdown, distributed stores) make agent memory slow and inconsistent. This Skill consolidates 7 legacy memory systems into a unified AgentDB backend with HNSW vector search, delivering 150x-12,500x faster semantic queries while preserving backward compatibility. ## Core Features & Use Cases - Unified Memory Service: Implements a single IMemoryBackend interface routing semantic queries through HNSW indexing and standard queries through AgentDB. - Data Migration Pipelines: Provides phased migration strategies for moving SQLite and Markdown memory stores into AgentDB with generated embeddings. - SONA Learning Integration: Stores and retrieves learning patterns with reward and adaptation metadata for cross-agent memory sharing. - Use Case: When upgrading a multi-agent orchestration system, use this Skill to consolidate scattered memory backends into one vector-indexed store, then validate the 150x-12,500x search speedup and 50-75% memory reduction targets. ## Quick Start Ask the agent to design an AgentDB unification strategy and migrate the existing SQLite and Markdown memory stores to HNSW-indexed vector search.