Reme (Remember Me)
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built When I read the prompt about building something for a loved one, I could think of one person, my mom. She runs a business, she's always busy and she skips her multivitamins, more than she takes it. I am not around always to remind her, and when I do I get the same reply, "lelungi baad mein" (I'll take it…
This story tells of a programmer building a tool called Reme to help her mother remember to take her daily multivitamin. The author's mother is often busy and forgets to take her vitamins, usually skipping them entirely. The author wanted a way to gently remind her without disrupting their conversations.
So, they created Reme, a small app that sends reminders through WhatsApp, the only app the mother uses for texting. The bot operates from the author's own phone number, so the messages never leave their laptop. Reme uses the Gemma 3.4B language model running locally through Ollama, a tool for running AI models. The model is trained to understand her replies and follow simple commands like "wait 10 minutes" or "I can't today, I'm upset stomach."
The app is quite simple. At around 11:45 after her breakfast, Reme asks "Mummy, nashta ho gaya?" meaning "Had breakfast?" If she says yes, it reminds her to take her vitamins in 15 minutes. The bot understands her standard replies like "Haan," "Ha leli," "10 min ruko," or "Aaj nahi lena" and waits accordingly. If she ignores three reminders, the bot stops nagging and sends a message to the author instead, asking if he should call her.
The story highlights the importance of simplicity in the AI model used for this project. The author tested every change against real messages from her mother, avoiding overcomplicating the model or letting it guess context. By keeping the model focused, the reminder system works reliably without exposing her personal information to outside AI companies.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
