What I Built

I built CareCue AI, an accessible, privacy-centric medication schedule companion designed for family caregivers and loved ones who manage multiple daily prescriptions.

My grandfather spends most weekdays home alone while my parents are at work and I am out for classes. Keeping track of his daily medications was a persistent challenge. Messy prescription notes with conflicting meal timings (e.g., "twice daily with meals") are hard to parse, and typical smartphone alarm apps are frustrating for him to configure. We spent too much time worrying about missed doses from afar, which made building a dead-simple, empathetic reminder companion a top priority

CareCue AI solves this through a straightforward flow:

Unstructured Prescription Ingestion: Caregivers paste or type rough doctor instructions directly into the interface.

AI Schedule Extraction: An open-weight AI model parses the notes into structured records, cleans up conversational filler, and splits multi-intake frequencies (such as morning, lunch, and dinner doses) into distinct timetable entries.

Editable Verification: Before committing to a schedule, users review the structured cards, adjust times or dosages if needed, and save them with one click.

Accessible Audio-Visual Alerts: When a dose is due, CareCue AI sounds a browser chime using the native Web Audio API and presents a high-contrast alert modal complete with an empathetic reminder cue, snooze option, and a one-click "Mark as Taken" action.

Code

AmjustGettingStarted / carecue-ai

A smart, privacy-first medicine reminder that turns messy prescriptions into timely audio alerts and structured schedules for family members, powered by open-source AI.

CareCue AI

HMV · 2026-10-02T14:06:54Z

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built I built CareCue AI , an accessible, privacy-centric medication schedule companion designed for family caregivers and loved ones who manage multiple daily prescriptions. My grandfather spends most weekdays home alone while my parents are at work and I am out for classes. Keeping track of his daily medications was a persistent challenge. Messy prescription notes with conflicting meal timings (e.g., "twice daily with meals") are hard to parse, and typical smartphone alarm apps are frustrating for him to configure. We spent too much time worrying about missed doses from afar, which made building a dead-simple, empathetic reminder companion a top priority CareCue AI solves this through a straightforward flow: Unstructured Prescription Ingestion: Caregivers paste or type rough doctor instructions directly into the interface. AI Schedule Extraction: An open-weight AI model parses the notes into structured records, cleans up conversational filler, and splits multi-intake frequencies (such as morning, lunch, and dinner doses) into distinct timetable entries. Editable Verification: Before committing to a schedule, users review the structured cards, adjust times or dosages if needed, and save them with one click. Accessible Audio-Visual Alerts: When a dose is due, CareCue AI sounds a browser chime using the native Web Audio API and presents a high-contrast alert modal complete with an empathetic reminder cue, snooze option, and a one-click "Mark as Taken" action. Demo Live Application: https://carecue-ai-yquo.onrender.com Code AmjustGettingStarted / carecue-ai A smart, privacy-first medicine reminder that turns messy prescriptions into timely audio alerts and structured schedules for family members, powered by open-source AI. CareCue AI Accessible, Privacy-Centric Medicine Reminder & Caregiver Dashboard Built with Next.js (App Router, TypeScript), Tailwind CSS, and shadcn/ui. Hacktoberfest Challenge 1 Compliant : Powered by Open-Source AI (Llama 3.1 / Gemma 2). 🌟 Overview & Key Features CareCue AI bridges the gap between messy medical prescriptions and reliable medication adherence: Intelligent Ingestion via Open-Source AI : Parses unstructured doctor notes, discharge summaries, or caregiver instructions. Extracts exact drug names, dosages, 24-hour schedules ( HH:MM ), and dietary constraints. Synthesizes an empathetic, warm, easy-to-read one-sentence reminder prompt ( friendlyCue ) tailored for family members or elderly relatives. Pre-loaded with three quick-sample presets Dad's Blood Pressure & Sugar Post-Surgery Recovery Grandma's Evening Routine Zero-Cloud Client Privacy & LocalStorage Persistence : Stores schedules, dose logs, and timestamps locally in the browser. Zero mandatory database setup — runs instantly on any device. In-Browser Web Audio API Chime & High-Contrast Alarms : Synthesized melodic… View on GitHub How I Built It The application is built using modern web standards and open-source tooling: Framework: Next.js (App Router, TypeScript) Styling & UI: Tailwind CSS and accessible component patterns inspired by shadcn/ui Open-Source AI Backend: Powered by an open-weight instruction-tuned model ( Llama 3.1 8B Instruct ) queried via an OpenAI-compatible inference endpoint. Sanitization & Splitting Pipeline: Implemented a dedicated post-processing module ( lib/prescriptionSanitizer.ts ) using regular expressions and time-slot mapping. This ensures medication names are clean of conversational glue words (like "take" or "and one" ) and automatically expands bundled frequencies into individual, scheduled daily events. Audio Engine: Developed a client-side chime generator via the browser's native AudioContext (HTML5 Web Audio API), producing clear sound alerts without depending on external media assets or heavy libraries. Hosting: Deployed on Render as a Node web service. Why Does Open Innovation Matter? Prescription habits, dosages, and medical timing data are deeply personal health details. Relying on closed, proprietary AI platforms introduces significant trade-offs: data can be logged to corporate telemetry pipelines, subject to vendor price shifts, or hidden behind black-box terms of service. Open innovation and open-weight models fundamentally shift control back to the user: Data Sovereignty & Health Privacy: Open-weight models like Llama allow healthcare-adjacent tools to run without funneling sensitive family routines into centralized corporate training silos. Self-Hostable Resilience: The exact same inference pipeline can be run locally using Ollama or embedded into self-hosted home servers without ongoing subscription barriers. Predictable, Long-Term Tooling: Open models empower independent developers to create vital accessibility tools for friends and relatives that remain dependable over time, free from arbitrary deprecations or forced API schema updates. Prize Categories Best Use of Render: The application is fully deployed and actively serving web requests as a Next.js service on Render.

Accessible, Privacy-Centric Medicine Reminder & Caregiver Dashboard
Built with Next.js (App Router, TypeScript), Tailwind CSS, and shadcn/ui.
Hacktoberfest Challenge 1 Compliant: Powered by Open-Source AI (Llama 3.1 / Gemma 2).

🌟 Overview & Key Features

CareCue AI bridges the gap between messy medical prescriptions and reliable medication adherence:

Intelligent Ingestion via Open-Source AI:
- Parses unstructured doctor notes, discharge summaries, or caregiver instructions.
- Extracts exact drug names, dosages, 24-hour schedules (HH:MM), and dietary constraints.
- Synthesizes an empathetic, warm, easy-to-read one-sentence reminder prompt (friendlyCue) tailored for family members or elderly relatives.
- Pre-loaded with three quick-sample presets
  - Dad's Blood Pressure & Sugar
  - Post-Surgery Recovery
  - Grandma's Evening Routine
Zero-Cloud Client Privacy & LocalStorage Persistence:
- Stores schedules, dose logs, and timestamps locally in the browser.
- Zero mandatory database setup — runs instantly on any device.
In-Browser Web Audio API Chime & High-Contrast Alarms:
- Synthesized melodic…

View on GitHub

How I Built It

The application is built using modern web standards and open-source tooling:

Framework: Next.js (App Router, TypeScript)

Styling & UI: Tailwind CSS and accessible component patterns inspired by shadcn/ui

Open-Source AI Backend: Powered by an open-weight instruction-tuned model (Llama 3.1 8B Instruct) queried via an OpenAI-compatible inference endpoint.

Sanitization & Splitting Pipeline: Implemented a dedicated post-processing module (lib/prescriptionSanitizer.ts) using regular expressions and time-slot mapping. This ensures medication names are clean of conversational glue words (like "take" or "and one") and automatically expands bundled frequencies into individual, scheduled daily events.

Audio Engine: Developed a client-side chime generator via the browser's native AudioContext (HTML5 Web Audio API), producing clear sound alerts without depending on external media assets or heavy libraries.

Hosting: Deployed on Render as a Node web service.

Why Does Open Innovation Matter?

Prescription habits, dosages, and medical timing data are deeply personal health details. Relying on closed, proprietary AI platforms introduces significant trade-offs: data can be logged to corporate telemetry pipelines, subject to vendor price shifts, or hidden behind black-box terms of service.

Open innovation and open-weight models fundamentally shift control back to the user:

Data Sovereignty & Health Privacy: Open-weight models like Llama allow healthcare-adjacent tools to run without funneling sensitive family routines into centralized corporate training silos.

Self-Hostable Resilience: The exact same inference pipeline can be run locally using Ollama or embedded into self-hosted home servers without ongoing subscription barriers.

Predictable, Long-Term Tooling: Open models empower independent developers to create vital accessibility tools for friends and relatives that remain dependable over time, free from arbitrary deprecations or forced API schema updates.

DEV Community

CareCue AI | Transforming Messy Prescriptions into Timely Reminders for Loved Ones