鱼皮AI导航
鱼皮AI导航
  • 主页
  • 社区
  • AI工具
  • AI知识库
  • AI提示词
  • MCP
  • Skills
  • AI学习资源
  • AI资讯
  • GitHub开源
登录/注册

reasoningbank-agentdb

支持智能体通过经验轨迹记录、成功判据评估、记忆提炼与模式识别实现自适应学习,依托高性能向量数据库加速检索与推理,在保持完全兼容的前提下显著提升决策优化与经验回放效率。

数据与分析
访问 GitHub
文档Skills.MD
name
ReasoningBank with AgentDB
description
Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition. Use when building self-learning agents, optimizing decision-making, or implementing experience replay systems.

ReasoningBank with AgentDB

What This Skill Does

Provides ReasoningBank adaptive learning patterns using AgentDB's high-performance backend (150x-12,500x faster). Enables agents to learn from experiences, judge outcomes, distill memories, and improve decision-making over time with 100% backward compatibility.

Performance: 150x faster pattern retrieval, 500x faster batch operations, <1ms memory access.

Prerequisites

  • Node.js 18+
  • AgentDB v1.0.7+ (via agentic-flow)
  • Understanding of reinforcement learning concepts (optional)

Quick Start with CLI

Initialize ReasoningBank Database

▼
bash
复制代码
# Initialize AgentDB for ReasoningBank npx agentdb@latest init ./.agentdb/reasoningbank.db --dimension 1536 # Start MCP server for Claude Code integration npx agentdb@latest mcp claude mcp add agentdb npx agentdb@latest mcp

Migrate from Legacy ReasoningBank

▼
bash
复制代码
# Automatic migration with validation npx agentdb@latest migrate --source .swarm/memory.db # Verify migration npx agentdb@latest stats ./.agentdb/reasoningbank.db

Quick Start with API

▼
typescript
复制代码
import { createAgentDBAdapter, computeEmbedding } from 'agentic-flow/reasoningbank'; // Initialize ReasoningBank with AgentDB const rb = await createAgentDBAdapter({ dbPath: '.agentdb/reasoningbank.db', enableLearning: true, // Enable learning plugins enableReasoning: true, // Enable reasoning agents cacheSize: 1000, // 1000 pattern cache }); // Store successful experience const query = "How to optimize database queries?"; const embedding = await computeEmbedding(query); await rb.insertPattern({ id: '', type: 'experience', domain: 'database-optimization', pattern_data: JSON.stringify({ embedding, pattern: { query, approach: 'indexing + query optimization', outcome: 'success', metrics: { latency_reduction: 0.85 } } }), confidence: 0.95, usage_count: 1, success_count: 1, created_at: Date.now(), last_used: Date.now(), }); // Retrieve similar experiences with reasoning const result = await rb.retrieveWithReasoning(embedding, { domain: 'database-optimization', k: 5, useMMR: true, // Diverse results synthesizeContext: true, // Rich context synthesis }); console.log('Memories:', result.memories); console.log('Context:', result.context); console.log('Patterns:', result.patterns);

Core ReasoningBank Concepts

1. Trajectory Tracking

Track agent execution paths and outcomes:

▼
typescript
复制代码
// Record trajectory (sequence of actions) const trajectory = { task: 'optimize-api-endpoint', steps: [ { action: 'analyze-bottleneck', result: 'found N+1 query' }, { action: 'add-eager-loading', result: 'reduced queries' }, { action: 'add-caching', result: 'improved latency' } ], outcome: 'success', metrics: { latency_before: 2500, latency_after: 150 } }; const embedding = await computeEmbedding(JSON.stringify(trajectory)); await rb.insertPattern({ id: '', type: 'trajectory', domain: 'api-optimization', pattern_data: JSON.stringify({ embedding, pattern: trajectory }), confidence: 0.9, usage_count: 1, success_count: 1, created_at: Date.now(), last_used: Date.now(), });

2. Verdict Judgment

Judge whether a trajectory was successful:

▼
typescript
复制代码
// Retrieve similar past trajectories const similar = await rb.retrieveWithReasoning(queryEmbedding, { domain: 'api-optimization', k: 10, }); // Judge based on similarity to successful patterns const verdict = similar.memories.filter(m => m.pattern.outcome === 'success' && m.similarity > 0.8 ).length > 5 ? 'likely_success' : 'needs_review'; console.log('Verdict:', verdict); console.log('Confidence:', similar.memories[0]?.similarity || 0);

3. Memory Distillation

Consolidate similar experiences into patterns:

▼
typescript
复制代码
// Get all experiences in domain const experiences = await rb.retrieveWithReasoning(embedding, { domain: 'api-optimization', k: 100, optimizeMemory: true, // Automatic consolidation }); // Distill into high-level pattern const distilledPattern = { domain: 'api-optimization', pattern: 'For N+1 queries: add eager loading, then cache', success_rate: 0.92, sample_size: experiences.memories.length, confidence: 0.95 }; await rb.insertPattern({ id: '', type: 'distilled-pattern', domain: 'api-optimization', pattern_data: JSON.stringify({ embedding: await computeEmbedding(JSON.stringify(distilledPattern)), pattern: distilledPattern }), confidence: 0.95, usage_count: 0, success_count: 0, created_at: Date.now(), last_used: Date.now(), });

Integration with Reasoning Agents

AgentDB provides 4 reasoning modules that enhance ReasoningBank:

1. PatternMatcher

Find similar successful patterns:

▼
typescript
复制代码
const result = await rb.retrieveWithReasoning(queryEmbedding, { domain: 'problem-solving', k: 10, useMMR: true, // Maximal Marginal Relevance for diversity }); // PatternMatcher returns diverse, relevant memories result.memories.forEach(mem => { console.log(`Pattern: ${mem.pattern.approach}`); console.log(`Similarity: ${mem.similarity}`); console.log(`Success Rate: ${mem.success_count / mem.usage_count}`); });

2. ContextSynthesizer

Generate rich context from multiple memories:

▼
typescript
复制代码
const result = await rb.retrieveWithReasoning(queryEmbedding, { domain: 'code-optimization', synthesizeContext: true, // Enable context synthesis k: 5, }); // ContextSynthesizer creates coherent narrative console.log('Synthesized Context:', result.context); // "Based on 5 similar optimizations, the most effective approach // involves profiling, identifying bottlenecks, and applying targeted // improvements. Success rate: 87%"

3. MemoryOptimizer

Automatically consolidate and prune:

▼
typescript
复制代码
const result = await rb.retrieveWithReasoning(queryEmbedding, { domain: 'testing', optimizeMemory: true, // Enable automatic optimization }); // MemoryOptimizer consolidates similar patterns and prunes low-quality console.log('Optimizations:', result.optimizations); // { consolidated: 15, pruned: 3, improved_quality: 0.12 }

4. ExperienceCurator

Filter by quality and relevance:

▼
typescript
复制代码
const result = await rb.retrieveWithReasoning(queryEmbedding, { domain: 'debugging', k: 20, minConfidence: 0.8, // Only high-confidence experiences }); // ExperienceCurator returns only quality experiences result.memories.forEach(mem => { console.log(`Confidence: ${mem.confidence}`); console.log(`Success Rate: ${mem.success_count / mem.usage_count}`); });

Legacy API Compatibility

AgentDB maintains 100% backward compatibility with legacy ReasoningBank:

▼
typescript
复制代码
import { retrieveMemories, judgeTrajectory, distillMemories } from 'agentic-flow/reasoningbank'; // Legacy API works unchanged (uses AgentDB backend automatically) const memories = await retrieveMemories(query, { domain: 'code-generation', agent: 'coder' }); const verdict = await judgeTrajectory(trajectory, query); const newMemories = await distillMemories( trajectory, verdict, query, { domain: 'code-generation' } );

Performance Characteristics

  • Pattern Search: 150x faster (100µs vs 15ms)
  • Memory Retrieval: <1ms (with cache)
  • Batch Insert: 500x faster (2ms vs 1s for 100 patterns)
  • Trajectory Judgment: <5ms (including retrieval + analysis)
  • Memory Distillation: <50ms (consolidate 100 patterns)

Advanced Patterns

Hierarchical Memory

Organize memories by abstraction level:

▼
typescript
复制代码
// Low-level: Specific implementation await rb.insertPattern({ type: 'concrete', domain: 'debugging/null-pointer', pattern_data: JSON.stringify({ embedding, pattern: { bug: 'NPE in UserService.getUser()', fix: 'Add null check' } }), confidence: 0.9, // ... }); // Mid-level: Pattern across similar cases await rb.insertPattern({ type: 'pattern', domain: 'debugging', pattern_data: JSON.stringify({ embedding, pattern: { category: 'null-pointer', approach: 'defensive-checks' } }), confidence: 0.85, // ... }); // High-level: General principle await rb.insertPattern({ type: 'principle', domain: 'software-engineering', pattern_data: JSON.stringify({ embedding, pattern: { principle: 'fail-fast with clear errors' } }), confidence: 0.95, // ... });

Multi-Domain Learning

Transfer learning across domains:

▼
typescript
复制代码
// Learn from backend optimization const backendExperience = await rb.retrieveWithReasoning(embedding, { domain: 'backend-optimization', k: 10, }); // Apply to frontend optimization const transferredKnowledge = backendExperience.memories.map(mem => ({ ...mem, domain: 'frontend-optimization', adapted: true, }));

CLI Operations

Database Management

▼
bash
复制代码
# Export trajectories and patterns npx agentdb@latest export ./.agentdb/reasoningbank.db ./backup.json # Import experiences npx agentdb@latest import ./experiences.json # Get statistics npx agentdb@latest stats ./.agentdb/reasoningbank.db # Shows: total patterns, domains, confidence distribution

Migration

▼
bash
复制代码
# Migrate from legacy ReasoningBank npx agentdb@latest migrate --source .swarm/memory.db --target .agentdb/reasoningbank.db # Validate migration npx agentdb@latest stats .agentdb/reasoningbank.db

Troubleshooting

Issue: Migration fails

▼
bash
复制代码
# Check source database exists ls -la .swarm/memory.db # Run with verbose logging DEBUG=agentdb:* npx agentdb@latest migrate --source .swarm/memory.db

Issue: Low confidence scores

▼
typescript
复制代码
// Enable context synthesis for better quality const result = await rb.retrieveWithReasoning(embedding, { synthesizeContext: true, useMMR: true, k: 10, });

Issue: Memory growing too large

▼
typescript
复制代码
// Enable automatic optimization const result = await rb.retrieveWithReasoning(embedding, { optimizeMemory: true, // Consolidates similar patterns }); // Or manually optimize await rb.optimize();

Learn More

  • AgentDB Integration: node_modules/agentic-flow/docs/AGENTDB_INTEGRATION.md
  • GitHub: https://github.com/ruvnet/agentic-flow/tree/main/packages/agentdb
  • MCP Integration: npx agentdb@latest mcp
  • Website: https://agentdb.ruv.io

Category: Machine Learning / Reinforcement Learning Difficulty: Intermediate Estimated Time: 20-30 minutes

数据与分析

快捷安装

复制到终端去安装 Skill

npxskillsaddruvnet/claude-flow--skill"reasoningbank-agentdb"
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
站长:程序员鱼皮 老鱼简历 商务合作 增值电信业务经营许可证
2026 鱼皮AI导航 | 沪ICP备19026706号-6
🔥热门工具
朱雀AI检测朱雀AI检测
朱雀AI检测助手朱雀AI检测助手
LovartLovart
老鱼简历老鱼简历
WritePass官网WritePass官网
面多多面多多
CursorCursor
星月写作星月写作
朱雀AI检测助手朱雀AI检测助手
零感AI零感AI
Skills 推荐
definition-of-done-generator
自动生成项目完成标准的规范定义与配置文件,提供符合企业级工作流要求的最佳实践指导,输出可直接投入生产环境的代码和验证结果,适用于需要标准化流程审批、合规审查及跨系统集成的复杂项目管理场景。
sagemaker-endpoint-deployer
自动化部署机器学习模型至云端服务端点,支持从配置生成到生产验证的全流程,适用于模型上线、服务监控与推理优化等场景,确保部署方案符合工业级标准。
docx
支持专业级 Word 文档的全生命周期处理,包括从零创建结构化文档、精准编辑内容、管理修订痕迹与批注、提取纯文本或原始 XML 数据、转换为 PDF 或图像用于视觉分析,适用于法律、学术及企业场景下的高保真文档协作与自动化处理。
skills-search
提供对 Claude Code 技能生态的全周期管理能力,支持按功能关键词检索技能、查看详细信息、安装或卸载指定技能,并区分用户级与项目级作用域,覆盖发现、评估、部署及维护各环节。
moai-foundation-core
构建高质量、可扩展的AI开发工作流,通过领域驱动设计与模块化架构实现需求规范先行,结合自动化质量门禁、精细化上下文管理与渐进式知识呈现,在保障安全与可维护性的同时提升开发效率与协作清晰度。