AgentDB Memory Patterns

What problem does it solve? AI agents lose all context between sessions, forcing users to repeat information and preventing agents from learning from past interactions. This Skill provides persistent memory patterns so agents can remember conversations, store facts, and improve over time. ## Core Features & Use Cases - Session and Long-Term Memory: Store conversation history per session and persist important facts like user preferences across sessions. - Pattern Learning with ReasoningBank: Store successful interaction patterns, retrieve them with vector search and MMR, and train learning plugins (Q-Learning, Decision Transformer, Actor-Critic, and more). - CLI and MCP Integration: Initialize databases, run queries, import/export vectors, and expose memory to Claude Code via an MCP server. - Use Case: Build a support chatbot that remembers each user's preferences, recalls prior conversations via vector search, and learns which responses succeeded using reinforcement learning plugins. ## Quick Start Set up an AgentDB database and add persistent session memory with pattern learning to my TypeScript agent project.