{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/6a024ebfec164188bd7de353f16efc57\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/6a024ebfec164188bd7de353f16efc57-6cc453a47c2f8a57.gif","duration":3352.9485,"title":"Hierarchical Memory Planning and Reasoning in AI 🤖","description":"In this video, I demonstrate how to utilize files as a hierarchical memory system within Claude Code, focusing on short-term, long-term, and core memories, as well as a diary for episodic memory. I walk through tasks such as organizing papers and saving memories about ongoing projects. I emphasize the importance of naming agents for better interaction and memory sharing. Additionally, I discuss the potential risks of memory poisoning and the need to manage what is remembered. I encourage viewers to implement these memory systems in their own workflows and be mindful of the information stored."}