CoffeePolice
Caffeine isn't the problem
What it does
Everyone says, "Stop caffeine 8 hours before bed." I did. Still slept terribly. Turns out, generic rules don't work; your cutoff depends on your bedtime, sensitivity, and how cups stack. Coffee Police shows real-time active caffeine, calculates YOUR cutoff time, recommends drinks by the hour, and generates sleep impact reports that make the pattern undeniable. Free. No ads. No subscription. Just clarity on when to stop.
Does a similar job
all alternatives →
- CACaff.ai a Caffeine Manager for better sleep and more energy2023 · apps.apple.com · ▲6
Hey HN, I often don't know if I can have a coffee at 2pm and started logging my caffeine intake so I wouldn't be up until 2am. For me it was never as easy as a cut off time (ie stop coffee at 1pm) because I vary the amount and timing of my coffee day to day. I made an app that helps you stay in your custom 'daytime target range' and under your 'bedtime target' caffeine level. It can predict how much caffeine you'll have at bedtime and tell you what time your caffeine will be below a configurable sleepable level. I also added a feature that gives you a notification 30 minutes before you can…
- CCCaffeine Clock – A beautiful and accurate caffeine tracker appOct 2025 · caffeineclock.app · ▲14
Hi guys! I would love to show you Caffeine Clock 2.0, a tracker I made that shows you your caffeine levels now and in the future, helping you have undisrupted sleep by timing your caffeine better. A bit of context - as a guy who drinks a lot of caffeine, I wanted to make a good caffeine tracking app for a long time, since nothing I found at the time was sufficient. I wanted to make an app that would be easy to use, show you exactly when you’d have enough caffeine to not have your sleep disrupted, and could add all the drinks I usually drink, for free. After several iterations, I am now…
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 · 18d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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
