Build a local AI baby monitor with safety rules
A local video LLM watches a camera feed against a YAML list of safety rules and beeps when one is broken.
Source
zeenolife on Hacker News · 2025-05-21 · Project link
Written in our own words. Credit to the original author. Link checked 2026-10-14.
What they did
A local video LLM watches a camera feed against a YAML list of safety rules and beeps when one is broken.
Result (as claimed)
Open-sourced; runs locally.
Tools they used
Cost: Pricing depends on the tools you pick; check each official pricing page.
Set it up
Define the job
Say exactly what you want done and what the agent may and may not do on your behalf.
Share only what is needed
Give Redis the minimum files or access required. Avoid sharing passwords in chat when a safer login flow exists.
Review the plan
Ask the agent to show its plan or draft before it acts, and approve each step that has real consequences.
Check the result
Confirm the outcome yourself (order placed, request sent, document understood) and keep a record.
Copy the full setup prompt
Paste into your agent and it will walk you through the setup, asking before anything that sends, posts or spends.
You are helping me set up this AI use case end to end in Claude Code. Goal: Build a local AI baby monitor with safety rules What the original author did: A local video LLM watches a camera feed against a YAML list of safety rules and beeps when one is broken. Reported result (as claimed by the author): Open-sourced; runs locally. Source: https://news.ycombinator.com/item?id=44051386 Tools they used: Redis, vLLM, Qwen, Streamlit Category: Personal & life Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Codex. Goal: Build a local AI baby monitor with safety rules What the original author did: A local video LLM watches a camera feed against a YAML list of safety rules and beeps when one is broken. Reported result (as claimed by the author): Open-sourced; runs locally. Source: https://news.ycombinator.com/item?id=44051386 Tools they used: Redis, vLLM, Qwen, Streamlit Category: Personal & life Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
You are helping me set up this AI use case end to end in Grok Bot. Goal: Build a local AI baby monitor with safety rules What the original author did: A local video LLM watches a camera feed against a YAML list of safety rules and beeps when one is broken. Reported result (as claimed by the author): Open-sourced; runs locally. Source: https://news.ycombinator.com/item?id=44051386 Tools they used: Redis, vLLM, Qwen, Streamlit Category: Personal & life Please: 1. Ask me 3 short questions about my situation (accounts I have, budget, what I want the output to look like). 2. Propose a step-by-step plan using these tools or cheaper alternatives, with the time and cost of each step. Use official pricing pages; say "check pricing" if unsure. 3. Then do the setup with me one step at a time, waiting for my OK before anything that sends messages, posts publicly, spends money or deletes data. 4. Finish with a checklist to run it again next time.
Related use cases
Run a local AI for your car on a Raspberry Pi
Ran a 35B Qwen model on a Pi with connectors to the car's OBD port and the maker's cloud service.
Give your automation a real app interface
Put a simple Streamlit UI on top of an n8n workflow so people can interact with it like an app.
Build your own AI assistant on Telegram as a first project
A hobbyist built a personal AI assistant on Telegram as his first Claude Code project.
Search hours of your video footage by description
Uses Gemini's native video embeddings to search raw footage with plain text queries such as a car cutting you off, with no transcription.