This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle
What I Built
wo weeks ago, I built my first app, Jason's Jotter, to help my friend with ADHD capture thoughts and reminders before they disappeared. Then vanish without clutter when finished
I didn't wait until I knew everything. I started with one simple idea, and a few friends soon asked to use it.
That idea has evolved into Things to Recall, a voice-first AI reminder application with individual user accounts, persistent storage, and a live website.
Users can speak reminders naturally instead of typing them. They can also review, edit, and delete their reminders while maintaining privacy.
Demo
Code
CrymsynRavyn
/
things-to-recall
a notepad to remember
Things to Recall 🎤
A voice-first, distraction-free reminder app for ADHD-friendly workflows.
One button. Talk. Reminders appear. Done.
What It Does
- Press the big button → speak what you need to remember
- AI listens → Whisper transcribes it → Gemma extracts the core reminder
- Reminders appear on a simple list
- Check them off → they fade away
- Undo within 10 seconds if you checked by mistake
No settings, no menus, no friction.
Tech Stack
- Frontend: HTML/CSS/JS with MediaRecorder
- Backend: Python Flask
- Speech-to-Text: faster-whisper (int8 CPU, 1-2 sec)
- Reminder Extraction: Ollama + Gemma3:4b (local LLM, open-weight)
- Storage: Local JSON file (no cloud, no databases)
All inference is local. No API keys. No closed services.
How It Works
- Press and hold the button → Browser records audio via MediaRecorder
- Release → Audio blob uploads to Flask backend
- faster-whisper transcribes → Speech converted to text on the server
- …
How I Built It
I developed Things to Recall using Python, Flask, SQLite, faster-whisper, Ollama, and Gemma 3.
When someone records a reminder, faster-whisper converts their speech into text. Gemma 3 then processes the transcription into a concise reminder that can be saved and managed.
SQLite stores reminders for individual users, while Flask handles the web application and authentication.
I deployed the application to an Oracle Cloud Ubuntu server and used Caddy to provide HTTPS access through my own domain.
The development process included building the interface, adding user accounts, connecting the database, troubleshooting errors, and testing the voice-reminder workflow.
Why Does Open Innovation Matter?
Open innovation made this project possible without requiring an expensive commercial AI service.
Locally hosted AI tools give me greater control over the application's behavior, deployment, and operating costs.
Most importantly, they gave me the opportunity to learn by building something useful.
I believe technology should be accessible to people with ideas, even when they are just beginning their development journey.
My First User
My caseworker, Alecia, saw a demonstration of my original app and asked, "Can I use this?"
She immediately recognized its potential to help her remember tasks and follow-ups while working with different clients.Her interest helped me realize that an application inspired by one person's needs could benefit many others.I value her input soI did not accept payment she likes the ease of use and the light weight remember until its finished then forget it ever happened affect of not collecting completed reminders or
Prize Categories
Best Use of Gemma,
Top comments (0)