The LangMem SDK is a library that helps agents learn and improve through long-term memory. It provides tooling to extract information from conversations, optimize agent behavior through prompt updates, and maintain long-term memory about behaviors, facts, and events. The SDK integrates natively with LangGraph's long-term memory layer and offers a managed service for additional long-term memory results. Its goal is to make it easier for anyone to build AI experiences that become smarter and more personalized over time. The SDK provides three types of memory: semantic, episodic, and procedural, each serving distinct functions when building adaptive agents. Semantic memory stores key facts and relationships, while episodic memory stores memories of past interactions. Procedural memory represents internalized knowledge of how to perform tasks. The SDK offers a managed service that provides additional long-term memory results for free, and it is compatible with any storage system and Agent framework.