Agentdb persistent memory patterns
Skill bg-szy/TOP-SKILLS/skills/marketplace/agentdb-persistent-memory-patterns
全球最大的 Claude Code 技能聚合库 · 收录 3900+ 来自 12+ 来源的技能,提供在线搜索与趋势分析看板 / The world's largest Claude Code skill aggregation hub — 3900+ skills from 12+ sources with online search and trend dashboard
npx -y skills add bg-szy/TOP-SKILLS --skill agentdb-persistent-memory-patternsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Implement persistent memory patterns for AI agents using AgentDB - session memory, long-term storage, pattern learning, and context management for stateful agents, chat systems, and intelligent assistants
SKILL.md
3.9 KB, as published. Nobody here has run it
AgentDB Persistent Memory Patterns
Overview
Implement persistent memory patterns for AI agents using AgentDB - session memory, long-term storage, pattern learning, and context management for stateful agents, chat systems, and intelligent assistants.
SOP Framework: 5-Phase Memory Implementation
Phase 1: Design Memory Architecture (1-2 hours)
- Define memory schemas (episodic, semantic, procedural)
- Plan storage layers (short-term, working, long-term)
- Design retrieval mechanisms
- Configure persistence strategies
Phase 2: Implement Storage Layer (2-3 hours)
- Create memory stores in AgentDB
- Implement session management
- Build long-term memory persistence
- Setup memory indexing
Phase 3: Test Memory Operations (1-2 hours)
- Validate store/retrieve operations
- Test memory consolidation
- Verify pattern recognition
- Benchmark performance
Phase 4: Optimize Performance (1-2 hours)
- Implement caching layers
- Optimize retrieval queries
- Add memory compression
- Performance tuning
Phase 5: Document Patterns (1 hour)
- Create usage documentation
- Document memory patterns
- Write integration examples
- Generate API documentation
Quick Start
import { AgentDB, MemoryManager } from 'agentdb-memory';
// Initialize memory system
const memoryDB = new AgentDB({
name: 'agent-memory',
dimensions: 768,
memory: {
sessionTTL: 3600,
consolidationInterval: 300,
maxSessionSize: 1000
}
});
const memoryManager = new MemoryManager({
database: memoryDB,
layers: ['episodic', 'semantic', 'procedural']
});
// Store memory
await memoryManager.store({
type: 'episodic',
content: 'User preferred dark theme',
context: { userId: '123', timestamp: Date.now() }
});
// Retrieve memory
const memories = await memoryManager.retrieve({
query: 'user preferences',
type: 'episodic',
limit: 10
});
Memory Patterns
Session Memory
const session = await memoryManager.createSession('user-123');
await session.store('conversation', messageHistory);
await session.store('preferences', userPrefs);
const context = await session.getContext();
Long-Term Storage
await memoryManager.consolidate({
from: 'working-memory',
to: 'long-term-memory',
strategy: 'importance-based'
});
Pattern Learning
const patterns = await memoryManager.learnPatterns({
memory: 'episodic',
algorithm: 'clustering',
minSupport: 0.1
});
Success Metrics
- Memory persists across agent restarts
- Retrieval latency < 50ms (p95)
- Pattern recognition accuracy > 85%
- Context maintained with 95% accuracy
- Memory consolidation working
Additional Resources
- Full documentation: SKILL.md
- Process guide: PROCESS.md
- AgentDB Memory Docs: https://agentdb.dev/docs/memory