Apply persistent memory patterns for AI agents using AgentDB. Implement session memory, configure long-term storage, enable pattern learning, and manage context across sessions. Use when building stateful agents, creating chat systems, or designing intelligent assistants that learn from interactions.
Inherits all available tools
Additional assets for this skill
This skill inherits all available tools. When active, it can use any tool Claude has access to.
examples/example-1-short-term.mdexamples/example-2-long-term.mdexamples/example-3-episodic.mdgraphviz/workflow.dotreadme.mdreferences/gold-tier-overview.mdreferences/memory-patterns.mdreferences/performance-tuning.mdreferences/retention-policies.mdresources/scripts/context_manager.shresources/scripts/pattern_learning.pyresources/scripts/session_memory.pyresources/templates/memory-layers.yamlresources/templates/retention-policy.jsonresources/templates/session-config.jsontests/test-1-session-memory.mdtests/test-2-long-term-storage.mdtests/test-3-pattern-learning.mdname: agentdb-memory-patterns description: Apply persistent memory patterns for AI agents using AgentDB. Implement session memory, configure long-term storage, enable pattern learning, and manage context across sessions. Use when building stateful agents, creating chat systems, or designing intelligent assistants that learn from interactions. version: 1.0.0 category: platforms tags:
Use this skill to implement memory management patterns for AI agents using AgentDB's persistent storage and ReasoningBank integration. Apply these patterns to enable agents to remember conversations, learn from interactions, and maintain context across sessions. Deploy triple-layer retention (24h/7d/30d+) for optimal memory organization.
Performance: 150x-12,500x faster than traditional solutions with 100% backward compatibility.
Install Node.js 18+ and AgentDB v1.0.7+. Ensure you have AgentDB via agentic-flow or standalone. Review agent architecture patterns before implementing memory systems.
Run these commands to set up your AgentDB instance with memory patterns:
# Initialize vector database
npx agentdb@latest init ./agents.db
# Or with custom dimensions
npx agentdb@latest init ./agents.db --dimension 768
# Use preset configurations
npx agentdb@latest init ./agents.db --preset large
# In-memory database for testing
npx agentdb@latest init ./memory.db --in-memory
# Start MCP server (integrates with Claude Code)
npx agentdb@latest mcp
# Add to Claude Code (one-time setup)
claude mcp add agentdb npx agentdb@latest mcp
# Interactive plugin wizard
npx agentdb@latest create-plugin
# Use template directly
npx agentdb@latest create-plugin -t decision-transformer -n my-agent
# Available templates:
# - decision-transformer (sequence modeling RL)
# - q-learning (value-based learning)
# - sarsa (on-policy TD learning)
# - actor-critic (policy gradient)
# - curiosity-driven (exploration-based)
import { createAgentDBAdapter } from 'agentic-flow/reasoningbank';
// Initialize with default configuration
const adapter = await createAgentDBAdapter({
dbPath: '.agentdb/reasoningbank.db',
enableLearning: true, // Enable learning plugins
enableReasoning: true, // Enable reasoning agents
quantizationType: 'scalar', // binary | scalar | product | none
cacheSize: 1000, // In-memory cache
});
// Store interaction memory
const patternId = await adapter.insertPattern({
id: '',
type: 'pattern',
domain: 'conversation',
pattern_data: JSON.stringify({
embedding: await computeEmbedding('What is the capital of France?'),
pattern: {
user: 'What is the capital of France?',
assistant: 'The capital of France is Paris.',
timestamp: Date.now()
}
}),
confidence: 0.95,
usage_count: 1,
success_count: 1,
created_at: Date.now(),
last_used: Date.now(),
});
// Retrieve context with reasoning
const context = await adapter.retrieveWithReasoning(queryEmbedding, {
domain: 'conversation',
k: 10,
useMMR: true, // Maximal Marginal Relevance
synthesizeContext: true, // Generate rich context
});
Apply these memory patterns to organize agent memory across multiple time horizons.
Implement session-based memory to track conversation history:
class SessionMemory {
async storeMessage(role: string, content: string) {
return await db.storeMemory({
sessionId: this.sessionId,
role,
content,
timestamp: Date.now()
});
}
async getSessionHistory(limit = 20) {
return await db.query({
filters: { sessionId: this.sessionId },
orderBy: 'timestamp',
limit
});
}
}
// Store important facts
await db.storeFact({
category: 'user_preference',
key: 'language',
value: 'English',
confidence: 1.0,
source: 'explicit'
});
// Retrieve facts
const prefs = await db.getFacts({
category: 'user_preference'
});
// Learn from successful interactions
await db.storePattern({
trigger: 'user_asks_time',
response: 'provide_formatted_time',
success: true,
context: { timezone: 'UTC' }
});
// Apply learned patterns
const pattern = await db.matchPattern(currentContext);
// Organize memory in hierarchy
await memory.organize({
immediate: recentMessages, // Last 10 messages
shortTerm: sessionContext, // Current session
longTerm: importantFacts, // Persistent facts
semantic: embeddedKnowledge // Vector search
});
// Periodically consolidate memories
await memory.consolidate({
strategy: 'importance', // Keep important memories
maxSize: 10000, // Size limit
minScore: 0.5 // Relevance threshold
});
# Query with vector embedding
npx agentdb@latest query ./agents.db "[0.1,0.2,0.3,...]"
# Top-k results
npx agentdb@latest query ./agents.db "[0.1,0.2,0.3]" -k 10
# With similarity threshold
npx agentdb@latest query ./agents.db "0.1 0.2 0.3" -t 0.75
# JSON output
npx agentdb@latest query ./agents.db "[...]" -f json
# Export vectors to file
npx agentdb@latest export ./agents.db ./backup.json
# Import vectors from file
npx agentdb@latest import ./backup.json
# Get database statistics
npx agentdb@latest stats ./agents.db
# Run performance benchmarks
npx agentdb@latest benchmark
# Results show:
# - Pattern Search: 150x faster (100µs vs 15ms)
# - Batch Insert: 500x faster (2ms vs 1s)
# - Large-scale Query: 12,500x faster (8ms vs 100s)
import { createAgentDBAdapter, migrateToAgentDB } from 'agentic-flow/reasoningbank';
// Migrate from legacy ReasoningBank
const result = await migrateToAgentDB(
'.swarm/memory.db', // Source (legacy)
'.agentdb/reasoningbank.db' // Destination (AgentDB)
);
console.log(`✅ Migrated ${result.patternsMigrated} patterns`);
// Train learning model
const adapter = await createAgentDBAdapter({
enableLearning: true,
});
await adapter.train({
epochs: 50,
batchSize: 32,
});
// Get optimal strategy with reasoning
const result = await adapter.retrieveWithReasoning(queryEmbedding, {
domain: 'task-planning',
synthesizeContext: true,
optimizeMemory: true,
});
# List available plugins
npx agentdb@latest list-plugins
# List plugin templates
npx agentdb@latest list-templates
# Get plugin info
npx agentdb@latest plugin-info <name>
stats command to track performance# Check database size
npx agentdb@latest stats ./agents.db
# Enable quantization
# Use 'binary' (32x smaller) or 'scalar' (4x smaller)
# Enable HNSW indexing and caching
# Results: <100µs search time
# Automatic migration with validation
npx agentdb@latest migrate --source .swarm/memory.db
npx agentdb@latest mcp for Claude Code