Can I migrate existing data from ReasoningBank?

Yes, it includes a dedicated migration utility and provides 100% backward compatibility with the ReasoningBank API while offering significant performance improvements.

What learning algorithms are supported?

The skill supports 9 total algorithms including Decision Transformer, Q-Learning, SARSA, Actor-Critic, and Curiosity-driven learning for agent behavior optimization.

How fast is retrieval with AgentDB Memory Patterns?

It is designed for extreme performance, offering vector search times under 100µs using HNSW indexing and pattern retrieval in less than 1ms with caching enabled.

Does this work with Claude Code via MCP?

Yes, it includes a built-in MCP server command that allows you to integrate AgentDB's memory capabilities directly into your Claude Code environment.

AgentDB Memory Patterns

Name: AgentDB Memory Patterns
Author: ellisapotheosis

byellisapotheosis

数据科学与机器学习

Implements high-performance persistent memory and reinforcement learning patterns for stateful AI agents.

关于

AgentDB Memory Patterns provides a sophisticated framework for managing AI agent state, enabling persistent memory, context retrieval, and continuous learning across sessions. It leverages AgentDB's high-performance vector storage and ReasoningBank integration to allow agents to remember past interactions, learn from successful patterns via reinforcement learning algorithms, and maintain rich hierarchical memory. This skill is ideal for developers building stateful chatbots, intelligent assistants, or complex autonomous agents requiring long-term context and behavioral optimization with performance speeds up to 12,500x faster than traditional solutions.

主要功能

Built-in reinforcement learning plugins including Decision Transformer and Q-Learning
Full MCP server integration for seamless use within Claude Code
Persistent session and long-term memory management for cross-session context
0 GitHub stars
High-performance vector storage with HNSW indexing for <100µs search times
Advanced memory consolidation and hierarchical organization strategies

使用场景

Building stateful AI assistants that remember user preferences and history over multiple sessions
Developing autonomous agents that optimize decision-making strategies through reinforcement learning
Creating complex chat systems with sophisticated context synthesis and retrieval-augmented generation

关于

主要功能

Built-in reinforcement learning plugins including Decision Transformer and Q-Learning
Full MCP server integration for seamless use within Claude Code
Persistent session and long-term memory management for cross-session context
0 GitHub stars
High-performance vector storage with HNSW indexing for <100µs search times
Advanced memory consolidation and hierarchical organization strategies

使用场景

Building stateful AI assistants that remember user preferences and history over multiple sessions
Developing autonomous agents that optimize decision-making strategies through reinforcement learning
Creating complex chat systems with sophisticated context synthesis and retrieval-augmented generation