{"slug": "fixit-ai-troubleshooter-for-non-technical-friends", "title": "FixIt: AI Troubleshooter for Non-Technical Friends", "summary": "A developer built HomeWatch, a local-first AI assistant that processes home camera footage on-device to generate an event timeline and answer natural-language questions about what happened, such as what a dog did while its owner was away. The system combines computer vision, local embeddings, and a local language model with retrieval-augmented generation, keeping footage inside the home and allowing users to swap in different open-weight models based on their hardware. The project is fully open source and can run offline once models are installed, avoiding per-video API costs.", "body_md": "*This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)*\n\nI built **HomeWatch**, a local-first AI assistant that helps my friend keep an eye on their home and, more specifically, their dog while they're away.\n\nThe problem was simple: they have a camera pointed at the main living area, but checking through hours of footage to figure out what happened during the day is tedious. They would often end up opening the camera app repeatedly just to answer questions like:\n\n“What did the dog do while I was out?”\n\nHomeWatch processes the camera footage locally and turns it into a simple timeline of what happened.\n\nInstead of watching hours of video, they can ask questions such as:\n\nThe system detects and summarises relevant events, allowing them to quickly understand what happened without manually reviewing the entire recording.\n\nIt can also highlight potentially unusual behaviour, such as the dog spending an unusually long amount of time waiting by the front door.\n\nMost importantly, the camera footage stays in the home. It isn't uploaded to a commercial AI service just to answer a question about what happened in someone's living room.\n\n**Live demo:** [https://homewatch.com](https://homewatch.com)\n\n**Demo video:** [https://www.youtube.com/watch?v=qEBLVw2QVHX](https://www.youtube.com/watch?v=qEBLVw2QVHX)\n\nThe demo shows a sample recording being processed into an event timeline, followed by natural-language questions about the events detected in the footage.\n\n**GitHub:** [https://github.com/tba/homewatch](https://github.com/tba/homewatch)\n\nHomeWatch is fully open source and can be run locally.\n\nHomeWatch is built around open-weight AI models running locally.\n\nThe application combines computer vision, video processing, local embeddings, and a local language model.\n\nThe basic pipeline looks like this:\n\n```\nCamera\n   │\n   ▼\nVideo Stream\n   │\n   ▼\nFrame / Event Detection\n   │\n   ├── Person detection\n   ├── Animal detection\n   ├── Object detection\n   └── Scene changes\n   │\n   ▼\nEvent Extraction\n   │\n   ▼\nLocal Vision Model\n   │\n   ▼\nEvent Database\n   │\n   ▼\nLocal LLM + RAG\n   │\n   ▼\nNatural-language answers\n```\n\nThe camera stream is processed locally. Relevant events are extracted rather than requiring the entire video history to be sent to an external service.\n\nThe events are stored with timestamps and contextual information, allowing the language model to retrieve the relevant events when a question is asked.\n\nFor example, a question such as:\n\n\"What did Luna do between 2pm and 4pm?\"\n\ncan be answered from the locally generated event history rather than asking the model to analyse two hours of video every time.\n\nThe AI model is also replaceable. Users can select different open-weight models depending on their available hardware, allowing the system to run on anything from a reasonably powerful desktop to a dedicated home server.\n\nHome camera footage is some of the most private data a person can generate.\n\nSending that footage to a third-party AI service would mean trusting another company with video from inside someone's home, potentially including family members, visitors, children, pets, conversations, and other sensitive information.\n\nUsing open models running locally changes that equation.\n\n**Privacy:** The camera footage never needs to leave the home.\n\nOffline operation: Once the models are installed, the system can continue working without an internet connection.\n\n**No per-video API costs:** Processing can happen locally without paying an external provider for every frame or request.\n\n**Model choice:** Different models can be tested and swapped without rebuilding the entire application around one proprietary API.\n\n**Control:** The detection, retrieval, prompting, and model layers are all accessible and configurable.\n\nThe open approach also makes the project more useful as a home-lab application. Someone can run it on their own server, experiment with different models, and adapt the behaviour to their particular cameras, pets, or household.\n\nThe project was developed with an AI coding agent, using the agent to help design the event-processing pipeline, implement the local inference workflow, and build the natural-language query interface.\n\nDevRelay session: [https://devrelay.tba.com/sessions/homewatch](https://devrelay.tba.com/sessions/homewatch)\n\nThe session shows the development process from the initial idea through to the working prototype.", "url": "https://wpnews.pro/news/fixit-ai-troubleshooter-for-non-technical-friends", "canonical_source": "https://dev.to/skully/fixit-ai-troubleshooter-for-non-technical-friends-2nbb", "published_at": "2026-10-03 14:01:54+00:00", "updated_at": "2026-10-03 14:08:04.662996+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "large-language-models", "ai-tools", "ai-products"], "entities": ["HomeWatch", "Hacktoberfest", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/fixit-ai-troubleshooter-for-non-technical-friends", "markdown": "https://wpnews.pro/news/fixit-ai-troubleshooter-for-non-technical-friends.md", "text": "https://wpnews.pro/news/fixit-ai-troubleshooter-for-non-technical-friends.txt", "jsonld": "https://wpnews.pro/news/fixit-ai-troubleshooter-for-non-technical-friends.jsonld"}}