{"slug": "studysprint-ai", "title": "StudySprint AI", "summary": "A developer built Slow Signal, a local-first task-sorting app that uses open-weight models via Ollama to categorize messy brain dumps into today, later, and let-go buckets and suggest a single first step. The app pairs a small HTML/CSS/JavaScript interface with a Java 17 server that filters out cloud models so personal notes stay on the local machine and can be processed offline once a model is downloaded. The developer has not measured time saved, framing that as a goal rather than a benchmark.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady](https://dev.to/challenges/hacktoberfest-week3-2026-10-19)*\n\nI built **Slow Signal**, a local-first brain dump sorter for the things I keep putting off. I paste in a messy list, and an open-weight AI model sorts it into what I could do today, what can wait, and what I can let go. It also suggests one tiny first step.\n\nThe idea is to make task sorting itself less of a task. No account, streak, or cloud AI service required.\n\n[https://pranjalkumar1307.github.io/StudySprint-AI/](https://pranjalkumar1307.github.io/StudySprint-AI/)\n\nTo run the app locally, install Ollama and run `ollama run gemma4:e2b`, then start the Java server with `mvn compile exec:java` and open `http://127.0.0.1:8787`.\n\n[https://github.com/PRANJALKUMAR1307/StudySprint-AI.git](https://github.com/PRANJALKUMAR1307/StudySprint-AI.git)\n\nSlow Signal has a small HTML, CSS, and JavaScript interface, with a Java 17 server connecting it to Ollama’s local API. The app lists locally installed models and asks the selected model to return a short, structured reflection: today, later, let go, and one first step.\n\nThe project is set up to use Gemma 4 through Ollama, and can also use other installed local models. The server filters out cloud models so brain dumps are sent to a local model.\n\nThese notes can include personal details. Running an open-weight model locally means they don’t need to be sent to a hosted AI service. After the model is downloaded, the app can generate reflections on my computer without an internet connection.\n\nOpen models also let me switch models and change how the assistant sorts tasks. That makes the AI part something I can inspect and adapt to the way I want to use the app.\n\nOne brain dump replaces manually sorting every task into categories. The app is designed to return a short list and a single tiny first step, so I can spend less energy organizing and more energy deciding what I actually want to do.\n\nI haven’t measured time saved yet, so I’m treating that as the goal rather than a benchmark.", "url": "https://wpnews.pro/news/studysprint-ai", "canonical_source": "https://dev.to/pranjal_kumar_1307/studysprint-ai-2m26", "published_at": "2026-10-21 09:27:28+00:00", "updated_at": "2026-10-21 09:40:21.295528+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "large-language-models", "ai-products"], "entities": ["Slow Signal", "Ollama", "Gemma 4", "Java 17", "StudySprint AI"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/studysprint-ai", "markdown": "https://wpnews.pro/news/studysprint-ai.md", "text": "https://wpnews.pro/news/studysprint-ai.txt", "jsonld": "https://wpnews.pro/news/studysprint-ai.jsonld"}}