{"slug": "recall-ai", "title": "Recall AI", "summary": "A developer and team built RecallAI, a visual memory assistant, at Cal Hacks 13.0 that combines YOLO-based object detection, visual embeddings, Claude for conversational queries, and FastAPI with SQLite for persistent storage. The developer's main contribution was a Temporal Memory system that timestamps observations so users can ask when and where an item was last seen, while grounding answers in recorded observations rather than inferences. The team also outlined an extension for remembering people and relationship check-ins with consent.", "body_md": "RecallAI: Building a Second Memory with Computer Vision at Cal Hacks 13.0\n\nThis is a submission for the MLH x DEV Writing Challenge.\n\nWhat I Built\n\nWhat if AI could remember the things we forget?\n\nAt 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 conversation.\n\nWe’ve all experienced that frustrating moment when we can’t find our keys, headphones, wallet, or something else important. Instead of searching everywhere, imagine simply asking:\n\n“Hey RecallAI, where did I last see my AirPods?”\n\nAnd getting a response like:\n\n“Your AirPods were last seen on your desk 23 minutes ago.”\n\nThat’s the idea behind RecallAI.\n\nHow It Works\n\nRecallAI combines computer vision, persistent storage, and an AI agent to turn everyday observations into searchable memories.\n\nOur architecture uses:\n\nRather than simply identifying objects, RecallAI builds a history of when and where those objects were observed.\n\nMy Contribution: Temporal Memory\n\nOne of my main contributions was developing RecallAI’s Temporal Memory system.\n\nObject detection answers the question, “What am I looking at?”\n\nTemporal Memory goes further by asking, “When did I last see it, and what do I know about its history?”\n\nThe system uses timestamped visual observations to support capabilities such as:\n\nAsk when an item was last observed and retrieve its most recent recorded sighting.\n\nSearch previous observations to understand where an object appeared at a particular point in time.\n\nRetrieve objects based on elapsed time, such as belongings that haven’t been observed recently.\n\nConnect historical observation data with the AI agent so users can ask questions conversationally.\n\nA particularly important engineering consideration was distinguishing what the system actually observed from what it could only infer.\n\nFor example, an object disappearing from the camera’s view doesn’t necessarily mean someone moved it or left it behind.\n\nBy grounding responses in recorded observations, we aimed to make RecallAI’s memory useful without overstating what the camera actually knew.\n\nBeyond Objects: Remembering People\n\nWe also explored a broader vision for RecallAI: helping people maintain meaningful relationships.\n\nImagine registering a friend, with their consent, through a scan or manual entry.\n\nRecallAI could remember when you last connected and gently remind you when it’s been a while.\n\nFor example:\n\n“It’s been three weeks since you last caught up with Alex. Maybe it’s time to reach out!”\n\nThis expands RecallAI’s potential beyond finding belongings into helping people stay connected.\n\nOur vision is simple: AI shouldn’t just help us remember things. It should help us remember what matters.\n\nDemo\n\nGitHub Repository: [https://github.com/Slickstarlol/CalHacksObjectFinder](https://github.com/Slickstarlol/CalHacksObjectFinder)\n\nDemo Video: [Insert your video or Devpost demo link]\n\nA typical RecallAI workflow looks like this:\n\nThe result is an interface that transforms camera observations into memories users can actually retrieve.\n\nPartner Technologies\n\nOur project brought together several technologies, each responsible for a different part of the memory pipeline.\n\nComputer Vision: YOLO enabled object detection, while visual embeddings helped match observations against registered belongings.\n\nClaude: Provided the conversational layer, allowing users to ask questions naturally instead of manually searching through recorded observations.\n\nFastAPI and SQLite: Connected the system’s components and provided persistent storage for the historical memory layer.\n\nMLH Partner Technology: [Add any official MLH partner technology your team actually integrated, including the API, SDK, implementation details, challenges, and what you learned. If none was used, state that clearly.]\n\nOne of the most valuable technical lessons was learning how to integrate different AI components into one coherent application. Detection, recognition, storage, retrieval, and natural-language interpretation all needed to work together.\n\nHackathon Experience\n\nBuilding RecallAI at Cal Hacks 13.0, hosted in Berkeley, California, was an incredible experience.\n\nWhat stood out to me was the atmosphere: being surrounded by ambitious builders, developers, and students who were genuinely excited about creating things.\n\nComing from the University of Birmingham in the UK, travelling to California for Cal Hacks was an opportunity to experience a completely different technology ecosystem.\n\nMy team and I had to make decisions quickly, divide engineering responsibilities, integrate our work, and turn an idea into something tangible within the hackathon’s limited timeframe.\n\nWe also learned that a compelling project doesn’t necessarily need to solve every problem imaginable. Sometimes the strongest approach is identifying one meaningful problem and building a focused solution around it.\n\nFor RecallAI, that problem was memory.\n\nWorking on Temporal Memory was particularly rewarding because it connected the technical infrastructure of our application with something users could immediately understand: being able to ask where something was and receive an answer based on actual observations.\n\nBeyond the code, Cal Hacks reminded me why I enjoy software engineering in the first place.\n\nIt’s the process of taking an idea, collaborating with other people, encountering unexpected problems, and eventually seeing something you built come to life.\n\nWhat’s Next?\n\nRecallAI has potential applications beyond locating everyday belongings.\n\nWe want to explore richer historical search, more reliable context-aware reminders, and ways to help people maintain their personal connections.\n\nUltimately, we’re interested in one question:\n\nWhat if technology could help us spend less time searching for things we’ve forgotten and more time focusing on the people and experiences that matter?\n\nThat’s the future we started exploring with RecallAI.\n\n⸻\n\nBuilt at Cal Hacks 13.0.\n\nGitHub: [https://github.com/Slickstarlol/CalHacksObjectFinder](https://github.com/Slickstarlol/CalHacksObjectFinder)", "url": "https://wpnews.pro/news/recall-ai", "canonical_source": "https://dev.to/rihaan_hashmani_3070e3d22/recall-ai-1ncm", "published_at": "2026-10-26 19:10:12+00:00", "updated_at": "2026-10-26 19:13:10.614115+00:00", "lang": "en", "topics": ["computer-vision", "ai-agents", "ai-tools", "large-language-models", "artificial-intelligence"], "entities": ["RecallAI", "Cal Hacks 13.0", "YOLO", "Claude", "FastAPI", "SQLite", "MLH"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/recall-ai", "markdown": "https://wpnews.pro/news/recall-ai.md", "text": "https://wpnews.pro/news/recall-ai.txt", "jsonld": "https://wpnews.pro/news/recall-ai.jsonld"}}