The context quality layer for AI agents

Key features

• MemorySemantic search — POST /api/search (local-vector, per-user isolated, compact → full → pack disclosure): Auto-indexed on every write
• Local-firstdatabase, vectors and logs stay on your machine.
• Personalevery AI assistant, every session starts from a context hub that already understands you — stop re-onboarding your AI.
• The layers you see — research cockpit, expert infer, memory health — map to the engine tiers below