{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"How We Agent","title":"Solving agent memory at the database layer","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/b602b35b\"></iframe>","width":"100%","height":180,"duration":2024,"description":"Most teams building agents run into the same problem: each agent accumulates its own private memory, and the organisation quietly acquires a dozen new information silos.\nThis episode is about addressing that at the database layer rather than the application layer. Yugabyte's new product, Meiko, gives agents shared memory and knowledge, so context compounds across agents.\nThe more interesting part is what they've built on it internally worth a listen if your agents keep re-learning what the last one already knew.","thumbnail_url":"https://img.transistorcdn.com/zm2cQVod7iUeHXB-VEI1a94SlLgwLH8qKNut5pbIhEk/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9jMGZj/MDExZjAzYTNiOGQ5/ZTE0Y2JjZDE0NDVh/M2FlNy5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}