V3 Memory Unification

ruvnet/ruflo/v3/@claude-flow/cli/.claude/skills/v3-memory-unification

作者 ruvnet58e0ae7e14e68aab45a4127d6f42f567bbcfb328無授權條款74K 個星標收錄於 2026年10月9日更新於 2026年10月9日儲存庫今天更新

Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).

僅含說明AI & Agents

AI 產生的概覽

將多個舊有記憶系統整合為搭配 HNSW 向量檢索的統一 AgentDB 後端。

功能: 此技能描述一套方案，把七個舊有記憶系統（MemoryManager、DistributedMemorySystem、SwarmMemory、AdvancedMemoryManager、SQLiteBackend、MarkdownBackend、HybridBackend）整併到單一 AgentDB 後端，並採用 HNSW 向量索引。內容提出 UnifiedMemoryService 介面、用於語意檢索的 HNSWIndexer，以及把 SQLite 與 Markdown 資料連同產生的嵌入向量遷移到 AgentDB 的遷移流程。文中也涵蓋 SONA 學習模式儲存，並列出檢索更快、記憶體用量更低、跨代理記憶共享等效能目標。
適用情境: 適用於規劃或記錄將多個分散的代理記憶儲存整併為單一向量檢索後端的情境。適合圍繞 AgentDB 導入、HNSW 索引，以及遷移現有 SQLite 或 Markdown 記憶資料的架構工作。
執行需求: 僅為說明性指示，未附帶指令碼。文中引用 TypeScript 元件（AgentDBAdapter、HNSWIndexer、DataMigrator）、嵌入向量產生器，以及 AgentDB/HNSW 執行環境，這些都需另行提供。

V3 Memory Unification

What This Skill Does

Consolidates disparate memory systems into unified AgentDB backend with HNSW vector search, achieving 150x-12,500x search performance improvements while maintaining backward compatibility.

Quick Start

bash

# Initialize memory unificationTask("Memory architecture", "Design AgentDB unification strategy", "v3-memory-specialist")
# AgentDB integrationTask("AgentDB setup", "Configure HNSW indexing and vector search", "v3-memory-specialist")
# Data migrationTask("Memory migration", "Migrate SQLite/Markdown to AgentDB", "v3-memory-specialist")

# Initialize memory unificationTask("Memory architecture", "Design AgentDB unification strategy", "v3-memory-specialist")
# AgentDB integrationTask("AgentDB setup", "Configure HNSW indexing and vector search", "v3-memory-specialist")
# Data migrationTask("Memory migration", "Migrate SQLite/Markdown to AgentDB", "v3-memory-specialist")

Systems to Unify

Legacy Systems → AgentDB

┌─────────────────────────────────────────┐│  • MemoryManager (basic operations)     ││  • DistributedMemorySystem (clustering) ││  • SwarmMemory (agent-specific)         ││  • AdvancedMemoryManager (features)     ││  • SQLiteBackend (structured)           ││  • MarkdownBackend (file-based)         ││  • HybridBackend (combination)          │└─────────────────────────────────────────┘                    ↓┌─────────────────────────────────────────┐│       🚀 AgentDB with HNSW             ││  • 150x-12,500x faster search          ││  • Unified query interface             ││  • Cross-agent memory sharing          ││  • SONA learning integration           │└─────────────────────────────────────────┘

┌─────────────────────────────────────────┐│  • MemoryManager (basic operations)     ││  • DistributedMemorySystem (clustering) ││  • SwarmMemory (agent-specific)         ││  • AdvancedMemoryManager (features)     ││  • SQLiteBackend (structured)           ││  • MarkdownBackend (file-based)         ││  • HybridBackend (combination)          │└─────────────────────────────────────────┘                    ↓┌─────────────────────────────────────────┐│       🚀 AgentDB with HNSW             ││  • 150x-12,500x faster search          ││  • Unified query interface             ││  • Cross-agent memory sharing          ││  • SONA learning integration           │└─────────────────────────────────────────┘

Implementation Architecture

Unified Memory Service

typescript

class UnifiedMemoryService implements IMemoryBackend {  constructor(    private agentdb: AgentDBAdapter,    private indexer: HNSWIndexer,    private migrator: DataMigrator  ) {}
  async store(entry: MemoryEntry): Promise<void> {    await this.agentdb.store(entry);    await this.indexer.index(entry);  }
  async query(query: MemoryQuery): Promise<MemoryEntry[]> {    if (query.semantic) {      return this.indexer.search(query); // 150x-12,500x faster    }    return this.agentdb.query(query);  }}

class UnifiedMemoryService implements IMemoryBackend {  constructor(    private agentdb: AgentDBAdapter,    private indexer: HNSWIndexer,    private migrator: DataMigrator  ) {}
  async store(entry: MemoryEntry): Promise<void> {    await this.agentdb.store(entry);    await this.indexer.index(entry);  }
  async query(query: MemoryQuery): Promise<MemoryEntry[]> {    if (query.semantic) {      return this.indexer.search(query); // 150x-12,500x faster    }    return this.agentdb.query(query);  }}

HNSW Vector Search

typescript

class HNSWIndexer {  constructor(dimensions: number = 1536) {    this.index = new HNSWIndex({      dimensions,      efConstruction: 200,      M: 16,      speedupTarget: '150x-12500x'    });  }
  async search(query: MemoryQuery): Promise<MemoryEntry[]> {    const embedding = await this.embedContent(query.content);    const results = this.index.search(embedding, query.limit || 10);    return this.retrieveEntries(results);  }}

class HNSWIndexer {  constructor(dimensions: number = 1536) {    this.index = new HNSWIndex({      dimensions,      efConstruction: 200,      M: 16,      speedupTarget: '150x-12500x'    });  }
  async search(query: MemoryQuery): Promise<MemoryEntry[]> {    const embedding = await this.embedContent(query.content);    const results = this.index.search(embedding, query.limit || 10);    return this.retrieveEntries(results);  }}

Migration Strategy

Phase 1: Foundation

typescript

// AgentDB adapter setupconst agentdb = new AgentDBAdapter({  dimensions: 1536,  indexType: 'HNSW',  speedupTarget: '150x-12500x'});

// AgentDB adapter setupconst agentdb = new AgentDBAdapter({  dimensions: 1536,  indexType: 'HNSW',  speedupTarget: '150x-12500x'});

Phase 2: Data Migration

typescript

// SQLite → AgentDBconst migrateFromSQLite = async () => {  const entries = await sqlite.getAll();  for (const entry of entries) {    const embedding = await generateEmbedding(entry.content);    await agentdb.store({ ...entry, embedding });  }};
// Markdown → AgentDBconst migrateFromMarkdown = async () => {  const files = await glob('**/*.md');  for (const file of files) {    const content = await fs.readFile(file, 'utf-8');    await agentdb.store({      id: generateId(),      content,      embedding: await generateEmbedding(content),      metadata: { originalFile: file }    });  }};

// SQLite → AgentDBconst migrateFromSQLite = async () => {  const entries = await sqlite.getAll();  for (const entry of entries) {    const embedding = await generateEmbedding(entry.content);    await agentdb.store({ ...entry, embedding });  }};
// Markdown → AgentDBconst migrateFromMarkdown = async () => {  const files = await glob('**/*.md');  for (const file of files) {    const content = await fs.readFile(file, 'utf-8');    await agentdb.store({      id: generateId(),      content,      embedding: await generateEmbedding(content),      metadata: { originalFile: file }    });  }};

SONA Integration

Learning Pattern Storage

typescript

class SONAMemoryIntegration {  async storePattern(pattern: LearningPattern): Promise<void> {    await this.memory.store({      id: pattern.id,      content: pattern.data,      metadata: {        sonaMode: pattern.mode,        reward: pattern.reward,        adaptationTime: pattern.adaptationTime      },      embedding: await this.generateEmbedding(pattern.data)    });  }
  async retrieveSimilarPatterns(query: string): Promise<LearningPattern[]> {    return this.memory.query({      type: 'semantic',      content: query,      filters: { type: 'learning_pattern' }    });  }}

class SONAMemoryIntegration {  async storePattern(pattern: LearningPattern): Promise<void> {    await this.memory.store({      id: pattern.id,      content: pattern.data,      metadata: {        sonaMode: pattern.mode,        reward: pattern.reward,        adaptationTime: pattern.adaptationTime      },      embedding: await this.generateEmbedding(pattern.data)    });  }
  async retrieveSimilarPatterns(query: string): Promise<LearningPattern[]> {    return this.memory.query({      type: 'semantic',      content: query,      filters: { type: 'learning_pattern' }    });  }}

Performance Targets

Search Speed: 150x-12,500x improvement via HNSW
Memory Usage: 50-75% reduction through optimization
Query Latency: <100ms for 1M+ entries
Cross-Agent Sharing: Real-time memory synchronization
SONA Integration: <0.05ms adaptation time

Success Metrics

All 7 legacy memory systems migrated to AgentDB
150x-12,500x search performance validated
50-75% memory usage reduction achieved
Backward compatibility maintained
SONA learning patterns integrated
Cross-agent memory sharing operational

來源與署名

來源：ruvnet/ruflo位於v3/@claude-flow/cli/.claude/skills/v3-memory-unification提交58e0ae7

授權條款：無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

V3 Memory Unification

V3 Memory Unification

What This Skill Does

Quick Start

Systems to Unify

Legacy Systems → AgentDB

Implementation Architecture

Unified Memory Service

HNSW Vector Search

Migration Strategy

Phase 1: Foundation

Phase 2: Data Migration

SONA Integration

Learning Pattern Storage

Performance Targets

Success Metrics

來源與署名

更多來自 ruvnet/ruflo 的技能

V3 Security Overhaul

V3 Swarm Coordination

V3 Performance Optimization

V3 MCP Optimization

V3 DDD Architecture

V3 Core Implementation

更多AI & Agents技能

Discernment Nudge

Skill Development

Plugin Structure

Command Development

Ppt Template Creator

Skill Development