What problem does it solve? AI agents lose context between sessions and cannot learn from past interactions. This Skill provides persistent memory patterns using AgentDB so agents can remember conversations, store long-term facts, and learn from successful interactions across sessions. ## Core Features & Use Cases - Session and Long-Term Memory: Store conversation history, user preferences, and facts with vector embeddings for semantic retrieval. - Pattern Learning with ReasoningBank: Train learning plugins (Decision Transformer, Q-Learning, Actor-Critic, and more) to improve agent behavior from experience. - High-Performance Vector Search: HNSW indexing, quantization, and caching deliver sub-millisecond pattern retrieval with 4-32x memory reduction. - Use Case: Build a customer support chatbot that remembers each user's preferences across sessions, retrieves relevant past resolutions via vector search, and improves its responses by training on successful interactions. ## Quick Start Initialize an AgentDB database and set up session memory for my agent so it can store and retrieve conversation history across sessions.
