Tododo: A Private To-Do App I Built for My Friend with Gemma + Ollama
This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built Tododo is a to-do app for one very particular list: my friend Yathurshan's. Yathurshan doesn't keep a normal to-do list. Almost every task is a big task with smaller steps inside it, and a lot of them come back every week. "Clean the room" is really desk, bed, floor, laundry , every Saturday. "Gym" is…
Tododo is a private to-do app built by the author for their friend Yathurshan. This app caters to people who have to-do lists consisting of large tasks broken down into smaller subtasks, many of which repeat on a regular basis. For example, cleaning the room is broken down into desk, bed, floor, and laundry, all of which are performed every Saturday.
Similarly, gym tasks like warm-up, workout, and stretch are repeated every Monday and Thursday. The app understands plain sentences like "Clean the room every Saturday: desk, bed, floor, laundry" and turns them into a task with four subtasks and a weekly repeat. When the scheduled time arrives, the subtasks automatically become unticked. The user never needs to retype anything.
The app works locally without the need for an internet connection and functions seamlessly even if the AI model is not running. It utilizes Gemma, an open-weight AI model, running locally through Ollama to process the user's input and return structured JSON containing the title, subtasks, and repeat rule. The server then validates the data before displaying it in a review card for the user to confirm before saving.
If Ollama is not available, a rule-based parser handles common phrasings to ensure the app remains functional. All the code for Tododo is open-source and requires only Python 3.9+.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.