{"name":"AI Baby Monitor: A Local Video-LLM Powered Solution for Child Safety","description":"The AI Baby Monitor is an innovative, privacy-first solution that leverages local Video-LLMs to enhance child supervision. It monitors a video stream against user-defined safety rules, issuing a gentle beep if a rule is broken. This tool acts as an additional pair of eyes, providing real-time alerts without compromising privacy.","github":"https://github.com/zeenolife/ai-baby-monitor","url":"https://osrepos.com/repo/zeenolife-ai-baby-monitor","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/zeenolife-ai-baby-monitor","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/zeenolife-ai-baby-monitor.md","json":"https://osrepos.com/repo/zeenolife-ai-baby-monitor.json","topics":["baby-monitor","video-llm","Python","AI","LLM","privacy","home-security","open-source"],"keywords":["baby-monitor","video-llm","Python","AI","LLM","privacy","home-security","open-source"],"stars":null,"summary":"The AI Baby Monitor is an innovative, privacy-first solution that leverages local Video-LLMs to enhance child supervision. It monitors a video stream against user-defined safety rules, issuing a gentle beep if a rule is broken. This tool acts as an additional pair of eyes, providing real-time alerts without compromising privacy.","content":"## Introduction\n\nThe AI Baby Monitor is a powerful, privacy-first project that utilizes local Video-LLMs to provide an intelligent monitoring system for children. Designed to be your \"second pair of eyes,\" it watches a video stream from a webcam or RTSP camera and applies a simple list of user-defined safety rules. If a rule is broken, the system issues a single, gentle beep, prompting you to quickly check on your baby. Everything runs locally on your network, ensuring complete privacy.\n\n## Installation\n\nGetting started with the AI Baby Monitor requires Docker, docker-compose, a GPU, and Python 3.12 with `uv`.\n\n**Prerequisites**: Docker + docker-compose, One GPU, Python 3.12 with [uv](https://github.com/astral-sh/uv){:target=\"_blank\"}\n\nbash\n# 1 — clone the repository\n$ git clone https://github.com/zeenolife/ai-baby-monitor.git && cd ai-baby-monitor\n\n# 2 — copy .env.template into .env\n$ cp .env.template .env\n\n# 3 — build & start all services (Redis, vLLM, video streamer, Streamlit viewer)\n$ docker compose up --build -d\n\n# 4 — start the watcher on the host. This is necessary for sound playback.\n$ uv run scripts/run_watcher.py --config-file configs/living_room.yaml\n\n# 5 — open the dashboard ? http://localhost:8501. You can also open the dashboard on your phone http://{host_network_ip}:8501\n\n\nPlease note, the first run will download the model (approximately 6 GB), build the Docker image, and may take a few minutes.\n\n## Examples\n\nThe project includes compelling demos that illustrate its functionality without putting children in danger.\n\n*   **\"No smartphones\" rule**: A demo shows an alert being fired when people are using smartphones, violating a predefined rule.\n*   **Baby walking safely**: Another demo illustrates the system correctly identifying a baby walking safely, with no alert issued.\n\nThese examples highlight the system's ability to discern between safe and potentially unsafe situations based on your custom rules.\n\n## Why Use It\n\nThe AI Baby Monitor stands out for several key reasons:\n\n*   **Private-first**: All processing occurs locally, ensuring no data ever leaves your network. This commitment to privacy is paramount for sensitive monitoring applications.\n*   **Realtime-ish Performance**: It operates efficiently on consumer GPUs, processing at approximately one request per second, making it practical for home use.\n*   **Advanced Video LLM**: By default, it uses the Qwen2.5 VL model, served through vLLM, providing sophisticated video analysis capabilities.\n*   **Minimalist Alerts**: A single, gentle beep serves as a deliberate, quiet notification, designed to prompt a quick glance rather than cause alarm.\n*   **Live Dashboard**: A Streamlit viewer offers a live stream and real-time LLM reasoning logs, giving you full transparency into the system's operations.\n*   **Easy Configuration**: Safety rules are defined in natural language within simple YAML files, making customization straightforward.\n*   **Multi-room Support**: The system can be configured to monitor multiple rooms simultaneously, adapting to various home setups.\n\nIt is important to remember that this project is not a replacement for adult supervision. It is intended as an additional safeguard for those brief moments of distraction, providing a timely alert when needed.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/zeenolife/ai-baby-monitor](https://github.com/zeenolife/ai-baby-monitor){:target=\"_blank\"}\n*   **DeepWiki**: [https://deepwiki.com/zeenolife/ai-baby-monitor](https://deepwiki.com/zeenolife/ai-baby-monitor){:target=\"_blank\"}","metrics":{"detailViews":2,"githubClicks":0},"dates":{"published":null,"modified":"2026-02-22T21:33:56.000Z"}}