I Built StudySaathi, a Private AI Study Buddy That Runs on Your Own Computer A developer built StudySaathi, a local-first AI study companion that runs on a user's own machine via Ollama and Google's open-weight gemma3:1b model, turning pasted class notes into simplified explanations, practice quizzes, and revision flashcards. Built with Flask for the Hacktoberfest Weekend Challenge: Build for a Friend, the app avoids API costs and keeps student notes private by never sending them to a third party. The developer made the parsers tolerant of small-model quirks such as stray labels and inconsistent quiz layouts, falling back to plain text when a response can't be parsed. This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend https://dev.to/challenges/hacktoberfest-weekend-2026-10-01 StudySaathi "study companion" is a local-first AI study buddy. You paste in your class notes, pick how you want to study, and it turns them into something easier to learn from: I built it for a friend who finds studying stressful. Big textbook chapters feel overwhelming, so I wanted a tool that breaks notes into small, calm steps he can go through at his own pace, without pressure and without needing an account or an internet connection to an AI service. I haven't deployed it, because it runs on your own computer with Ollama. Here is what it looks like, using Biology notes on photosynthesis: The app also has a light/dark mode toggle in the top bar. I tested all three modes myself with Biology notes on photosynthesis, and the testing shaped the app: gemma3:1b sometimes added stray labels like "Flashcard 5" to answers, or laid out quizzes differently each time. I made the parsers tolerant of those variations, and if a response still can't be read, the app shows it as plain text instead of breaking. StudySaathi is a local-first AI study buddy built with Flask, Ollama, and Gemma. Paste your class notes and choose how you want to study: get a simpler explanation, generate a practice quiz, or create revision flashcards. It was built for the Hacktoberfest Weekend Challenge: Build for a Friend — the idea is to make studying feel a little less stressful and help a friend revise at their own pace. Screenshot of StudySaathi generating a practice quiz from Biology notes about photosynthesis: Screenshot of StudySaathi generating a Explanation from Biology notes about photosynthesis: Screenshot of StudySaathi generating a flashcard from Biology notes about photosynthesis: /api/study . It takes the notes and a mode, wraps them in a task-specific prompt explain, quiz or flashcards , and sends it to Ollama running on the same machine. FRONT: / BACK: format, and the quiz and explanation parsers handle the different layouts small models produce. If a response doesn't match the expected format, the app shows it as plain text instead of breaking. OLLAMA MODEL environment variable. A study tool is only useful to the people who can actually use it, and many students can't pay for API subscriptions or don't want to send their notes to a third party. Open-weight models made a different design possible: A closed API would have meant ongoing costs and sending a student's notes elsewhere, which is the wrong trade-off for something meant to make studying feel safe and low-pressure. Best Use of Gemma: StudySaathi runs on Google's open-weight Gemma model gemma3:1b , served locally through Ollama. All three study modes explanations, quizzes and flashcards are generated by Gemma, and the app is built around turning its text output into interactive study views.