🧠 Intelligence & Memory

The system stores successful patterns in vector memory, builds a knowledge graph for structural understanding, learns from outcomes via neural networks, and adapts routing based on what works best.

Layer	Components	What It Does
Memory	HNSW, AgentDB, Cache	Stores and retrieves patterns with fast HNSW search
Knowledge Graph	MemoryGraph, PageRank, Communities	Identifies influential insights, detects clusters (ADR-049)
Self-Learning	LearningBridge, SONA, ReasoningBank	Triggers learning from insights, confidence lifecycle (ADR-049)
Agent Scopes	AgentMemoryScope, 3-scope dirs	Per-agent isolation + cross-agent knowledge transfer (ADR-049)
Embeddings	ONNX Runtime, MiniLM	Local vectors without API calls (faster with ONNX runtime)
Learning	SONA, MoE, ReasoningBank	Self-improves from results (sub-millisecond pattern matching)
Fine-tuning	MicroLoRA, EWC++	Lightweight adaptation without full retraining