KiddoCare
Calm AI guidance when your child is sick at 2am
What it does
My wife said, "I feel lost when the kids are sick at 2am - I use ChatGPT, but it doesn't feel right." So we built KiddoCare. Talk to it by voice, describe symptoms, and get a clear answer: stay home, see a clinic, or go to the hospital. It tracks temperatures, reminds you about medication doses, and builds a PDF timeline for the doctor. Not a replacement for medical advice - a calm companion that helps you until you can see a professional. Designed for parents. Free on iOS & Android.
Does the same job
all alternatives →
- ABAI Baby Monitor – local Video-LLM that beeps when safety rules break2025 · github.com · ▲94
Hi HN! I built AI Baby Monitor – a tiny stack (Redis + vLLM + Streamlit) that watches a video stream and a YAML list of safety rules. If the model spots a rule being broken it plays beep sound, so you can quickly glance over and check on your baby. Why? When we bought a crib for our daughter, the first thing she tried was climbing over the rail :/ I got a bit paranoid about constantly watching her over, so I thought of a helper that can *actively* watch the baby, while parents could stay *semi-actively* alert. It’s meant to be an additional set of eyes, and *not* a replacement for the…
- RMReview my startup, Kiddom - made for kids2013 · itunes.apple.com · ▲9
Hey everyone, I would like to tell HN about our startup and our first product, an iPad app. HN has helped me a lot through the ups and downs of making a product and I would really like to get feedback from the HN community. Kiddom is a smart learning environment based on the iPad. It provides an integrated system for parents to download learning apps, assign them to multiple children according to skill, monitor child performance and get some good insights into how well your child is learning Kiddom strikes the right balance between entertainment and education, and helps parents and teachers…
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
