Kabit – A Simple Habit Tracker
I have used a lot of habit-tracking apps and most of them are filled with features that are not useful to me, sometimes UI is a mess etc. I wanted to build an app that was simple and useful. I wasn't sure about GPT ability but wanted to give it a try. There was a lot of trial and error, especially in figuring out the logic of the streak counter, which took a lot of time. I have spent some time polishing the UI as well. Although not a perfect app, I think I have a good tracker. I am planning to add more features and would love to know your thoughts and feedback. Thanks
In plain words
Kabit is a habit-tracking app designed for users who find existing trackers overly complex or poorly designed. It focuses on simplicity and usability, featuring a clean interface and a streak counter to monitor habit consistency. The app integrates AI capabilities and is available on Apple devices. The maker plans to add additional features based on user feedback.
written from the facts on this page · September 2026
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 · 16d 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 · 26d ago · cactuscompute.com
Launched alongside, October 2024
the whole month →
Softr for Notion▲925Turn Notion databases into portals & apps with no code
Dev tools · 2024 · softr.io
One inbox for all your work discussions
Work · 2024 · generalcollaboration.com