🏗️ Architecture

Domain-Driven Design with bounded contexts, clean architecture, and measured performance across all topologies.

V3 Module Structure

Module	Purpose	Key Features
@claude-flow/hooks	Event-driven lifecycle	ReasoningBank, 27 hooks, pattern learning
@claude-flow/memory	Unified vector storage	AgentDB, RVF binary format, HnswLite, RvfMigrator, SONA persistence, LearningBridge, MemoryGraph
@claude-flow/security	CVE remediation	Input validation, path security, AIDefence
@claude-flow/swarm	Multi-agent coordination	6 topologies, Byzantine consensus, auto-scaling
@claude-flow/plugins	WASM extensions	RuVector plugins, semantic search, intent routing
@claude-flow/cli	Command interface	26 commands, 140+ subcommands, shell completions
@claude-flow/neural	Self-learning	SONA, 9 RL algorithms, EWC++ memory preservation
@claude-flow/testing	Quality assurance	London School TDD, Vitest, fixtures, mocks
@claude-flow/deployment	Release automation	Versioning, changelogs, NPM publishing
@claude-flow/shared	Common utilities	Types, validation schemas, RvfEventLog, constants
@claude-flow/browser	Browser automation	59 MCP tools, element refs, trajectory learning

Architecture Principles

Principle	Implementation	Benefit
Bounded Contexts	Each module owns its domain	No cross-module coupling
Dependency Injection	Constructor-based DI	Testable, mockable components
Event Sourcing	All state changes as events	Full audit trail, replay capability
CQRS	Separate read/write paths	Optimized queries, scalable writes
Clean Architecture	Domain → Application → Infrastructure	Business logic isolation

Performance Benchmarks

Benchmarks measured on Node.js 20+ with local SQLite. Results vary by hardware and workload.

Category	Metric	Target	Status
Startup	CLI cold start	<500ms	✅ Met
Startup	MCP server init	<400ms	✅ Met
Memory	HNSW search	<1ms	✅ Sub-ms
Memory	Pattern retrieval	<10ms	✅ Met
Swarm	Agent spawn	<200ms	✅ Met
Swarm	Consensus latency	<100ms	✅ Met
Neural	SONA adaptation	<0.05ms	⚡ Benchmarked
Graph	Build (1k nodes)	<200ms	✅ Met
Graph	PageRank (1k nodes)	<100ms	✅ Met
Learning	Insight recording	<5ms	✅ Met
Learning	Consolidation	<500ms	✅ Met
Task	Success rate	95%+	✅ Met

Topology Performance

Topology	Agents	Execution	Memory	Best For
Centralized	2-3	0.14-0.20s	180-256 MB	Simple tasks, single coordinator
Distributed	4-5	0.10-0.12s	128-160 MB	Parallel processing, speed
Hierarchical	6+	0.20s	256 MB	Complex tasks, clear authority
Mesh	4+	0.15s	192 MB	Collaborative, fault-tolerant
Hybrid	7+	0.18s	320 MB	Multi-domain, mixed workloads
Adaptive	2+	Variable	Dynamic	Auto-scaling, unpredictable load