AI Dev 25 | Harrison Chase: Long Term Memory with LangGraph скачать в хорошем качестве

AI Dev 25 | Harrison Chase: Long Term Memory with LangGraph

How do you build AI agents that remember, learn, and adapt over time? During AI Dev 25, Harrison Chase, Co-founder and CEO of LangChain, introduced the core concepts of long-term memory in AI agents—and how to implement them using LangGraph. The session covered three key memory types: – Semantic memory (facts and information) – Procedural memory (skills and behaviors) – Episodic memory (past interactions and events) To bring these ideas to life, Harrison walked through building a personalized email assistant that uses all three memory types to create more intelligent and context-aware interactions. Keep building, DeepLearning.AI