Recall AI
RecallAI: Building a Second Memory with Computer Vision at Cal Hacks 13.0 This is a submission for the MLH x DEV Writing Challenge. What I Built What if AI could remember the things we forget? At Cal Hacks 13.0, my team and I built RecallAI, an AI-powered visual memory assistant designed to help people remember where they last saw their belongings and retrieve those memories through natural…
At Cal Hacks 13.0, a team built RecallAI, an AI-powered visual memory assistant that helps users remember where they last saw their belongings. This system combines computer vision, persistent storage, and an AI agent to remember and retrieve memories through natural conversation. The team's main focus was developing a Temporal Memory system, which adds context to object detection by remembering when and where items were observed.
By integrating technologies like YOLO, visual embeddings, SQLite, Claude, and FastAPI, RecallAI can answer questions like "Where did I last see my AirPods?" and provide a timestamped response. The project also explored remembering people, such as friends, by storing their connection history and reminding users to stay in touch. The experience at Cal Hacks taught the team about integrating various AI components and the importance of focusing on a meaningful problem when building a solution.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
