skills.rest
KentwareDemo
KentwareDemoCOMMUNITY
Explore all skills by this author →
GitHub

AgentDB Memory Patterns

Implement persistent memory patterns for AI agents using AgentDB vector storage.

1|Updated Jun 3, 2026
Search Tags:#embeddings#vector database#mcp#reasoningbank#agentdb#agent memory#pattern learning
One-click install
npx skills add https://github.com/KentwareDemo/RuView --skill agentdb-memory-patterns-kentwaredemo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: AgentDB Memory Patterns
Source: https://github.com/KentwareDemo/RuView/tree/main/.claude/skills/agentdb-memory-patterns
Command: npx skills add https://github.com/KentwareDemo/RuView --skill agentdb-memory-patterns-kentwaredemo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agentdb, agentic-flow.

What problem does it solve? AI agents lose context between sessions and cannot learn from past interactions, forcing developers to rebuild memory, retrieval, and learning infrastructure from scratch. ## Core Features & Use Cases - Session and Long-Term Memory: Store conversation history, user facts, and preferences with persistent vector-backed storage. - Pattern Learning and Retrieval: Store interaction patterns, retrieve them with HNSW vector search and MMR, and train learning plugins such as Decision Transformer, Q-Learning, and Actor-Critic. - ReasoningBank Integration: Migrate legacy ReasoningBank databases, synthesize context with reasoning agents, and optimize memory through consolidation and quantization. - Use Case: Build a chat assistant that remembers user preferences across sessions, retrieves relevant past conversations via embedding search, and improves its responses by training on successful interactions. ## Quick Start Initialize an AgentDB database and create a memory adapter that stores conversation patterns and retrieves context with reasoning for my agent.

Frequently Asked Questions about AgentDB Memory Patterns

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add persistent memory to an AI agent with AgentDB?▼

Initialize a database with npx agentdb init, then create an adapter via createAgentDBAdapter from agentic-flow/reasoningbank. Store interactions with insertPattern and retrieve context using retrieveWithReasoning with embedding-based search.

How to integrate AgentDB memory with Claude Code?▼

Run npx agentdb mcp to start the MCP server, then register it once with claude mcp add agentdb npx agentdb mcp. This exposes AgentDB memory operations directly to Claude Code sessions.

What learning algorithms does AgentDB support?▼

AgentDB provides nine learning plugins: Decision Transformer, Q-Learning, SARSA, Actor-Critic, Active Learning, Adversarial Training, Curriculum Learning, Federated Learning, and Multi-task Learning. Create one with npx agentdb create-plugin using a template.

Can I migrate from legacy ReasoningBank to AgentDB?▼

Yes, use migrateToAgentDB from agentic-flow/reasoningbank with the source legacy database path and destination AgentDB path. The migration reports how many patterns were transferred and maintains full API backward compatibility.

Why is my AgentDB database growing too large?▼

Large databases result from unquantized vector storage. Enable binary quantization for 32x memory reduction or scalar for 4x reduction, and check current usage with npx agentdb stats on your database file.

Related Skills

Explore More Software Engineering Skills→
ciniencecinience
396

alicloud-ai-search-text-embedding

Generate text embeddings using Alibaba Cloud Model Studio models.

Community
Basic
jvdominojvdomino

domino-model-monitoring

Monitor deployed Domino models for drift, quality, and alerts.

Community
Advanced
ruvnetruvnet
70.1k

observe-metrics

Aggregates system metrics from memory namespaces and flags anomalies against baselines.

Community
Intermediate
superfhpsuperfhp

qdrant-vector-search

Perform vector similarity search via REST and gRPC APIs for RAG systems.

Community
Advanced