CycleCare: a private, local cycle companion powered by Gemma and Ollama
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built CycleCare is a small web app that estimates where I am in my menstrual cycle, lets me log symptoms, mood and energy, and then asks a local AI model for general self-care and meal ideas for the day. The friend I built it for is me. I wanted a simple way to understand my cycle without creating an account…
CycleCare is a local web app designed for menstrual cycle tracking and wellness suggestions. Developed by Aksharapsit1256, it utilizes the Gemma 2B open-weight AI model running locally on Ollama. The app runs on the user's own laptop, without requiring an account or storing data on cloud servers. It allows users to input their last period date, average cycle length, and food preferences.
Daily symptom, mood, energy level, and notes are logged. When the user requests suggestions, the backend fetches data from a local SQLite database, constructs a prompt including the cycle day, phase, symptoms, preferences, and restrictions, and sends it to the Ollama API for AI-generated responses. The response is then parsed and displayed in the UI, offering recommendations for self-care, hydration, movement, sleep, 2-3 meal ideas, and one piece of guidance.
The system prompt instructs the model not to provide medical diagnoses or medication recommendations. If Ollama is not running, the app gracefully falls back to a generic, AI-generated plan. Users can easily swap the AI model by changing a single configuration setting. Safety is emphasized, as the app is a wellness companion and not a medical tool, and does not replace professional medical advice.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
