agentsclimarketplace

Agentdb persistent memory patterns

Skill aiskillstore/marketplace/skills/dnyoussef/agentdb-persistent-memory-patterns

Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

Install
npx -y skills add aiskillstore/marketplace --skill agentdb-persistent-memory-patterns

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing 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.

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

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.