{"slug": "greenbreak-ai-less-scrolling-more-living", "title": "GreenBreak AI 🌱 — Less Scrolling, More Living!", "summary": "A developer built GreenBreak AI, a Python and web application that uses the locally run gemma2:2b model through Ollama to generate short outdoor break suggestions, aiming to replace casual scrolling with time outside. The backend sends structured generation requests to the local Ollama service, validates the model's responses, and falls back to template-based plans when AI generation fails, avoiding per-request cloud inference costs. The project is distributed on GitHub under Google's Gemma Terms of Use, which the developer notes is not an OSI-approved open-source license.", "body_md": "What if we used our screen breaks to reconnect with the outdoors instead of scrolling through another feed?\n\nThat's the idea behind **GreenBreak AI** — a project that encourages people to step away from their screens and enjoy small, meaningful outdoor activities.\n\nWe spend a lot of time looking at screens, even when we only intended to check something for a few minutes. Taking a break can easily turn into more scrolling.\n\nI wanted to build something that makes it easier to choose an outdoor activity instead.\n\n`gemma2:2b` model to generate break-plan suggestions locally.\nThe goal is simple: make it easier to replace a few minutes of scrolling with a refreshing break outdoors.\n\nGreenBreak AI combines a Python backend with a web frontend.\n\nWhen a user requests a break plan, the backend sends a structured generation request to a locally running Ollama service. The model's response is validated before being returned to the frontend. If AI generation fails, the application can use the template-based fallback.\n\nThis approach keeps the core experience available even when the local model cannot generate a response.\n\nI used **Gemma 2 2B (`gemma2:2b`) through Ollama**.\n\nInstead of relying on a paid, hosted AI API, the application can generate suggestions using a model running on the user's own computer. This avoids per-request cloud inference charges, although running the model still requires suitable local hardware and resources.\n\nThe model is distributed under Google's Gemma Terms of Use. It is an open-weight model with specific license conditions, so I am not claiming that it is OSI-approved open-source software.\n\n```\ngit clone https://github.com/Sri-Indu/GreenBreak-AI.git\ncd GreenBreak-AI\n```\n\nCreate and activate a Python virtual environment if desired, then install the project's requirements:\n\n```\npython -m pip install -r requirements.txt\n```\n\nInstall Ollama and make sure the `gemma2:2b` model is available locally.\n\nIf you do not already have the model, run:\n\n```\nollama pull gemma2:2b\n```\n\nIf it is already installed, you do not need to download it again. Ensure the Ollama service is running.\n\nFrom the project directory, run:\n\n```\npython -m uvicorn backend.main:app --host 127.0.0.1 --port 8000\n```\n\nFollow the frontend instructions in the repository README to open the application locally.\n\nIf Ollama is unavailable, the template fallback can provide break plans instead.\n\nI ran the Python test suite after integrating local AI generation:\n\nThese results verify the tested application behavior. Actual AI generation also depends on the local Ollama service and model being available.\n\nI wanted to explore how AI could support healthier digital habits without requiring a paid hosted AI API.\n\nLocal inference gives developers an opportunity to experiment with AI on their own machines, understand how model integration works, and build useful applications with fewer external service dependencies.\n\nThis project also helped me learn about structured model responses, backend validation, error handling, and fallback behavior.\n\nA short break outside can be more meaningful than another few minutes scrolling.\n\nWith GreenBreak AI, I hope to make those small breaks easier to plan — one outdoor activity at a time.\n\nThanks for reading! 🌱", "url": "https://wpnews.pro/news/greenbreak-ai-less-scrolling-more-living", "canonical_source": "https://dev.to/sriindu/greenbreak-ai-less-scrolling-more-living-3l2e", "published_at": "2026-10-10 11:05:37+00:00", "updated_at": "2026-10-10 11:13:21.868396+00:00", "lang": "en", "topics": ["ai-tools", "generative-ai", "large-language-models", "ai-products"], "entities": ["GreenBreak AI", "Ollama", "Gemma 2 2B", "Google", "GitHub", "Sri-Indu"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/greenbreak-ai-less-scrolling-more-living", "markdown": "https://wpnews.pro/news/greenbreak-ai-less-scrolling-more-living.md", "text": "https://wpnews.pro/news/greenbreak-ai-less-scrolling-more-living.txt", "jsonld": "https://wpnews.pro/news/greenbreak-ai-less-scrolling-more-living.jsonld"}}