The latest articles on DEV Community by Sagar Rana (@sagarrana25280). https://dev.to/sagarrana25280 https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4162010%2F4a92de1d-bfe7-4239-8cac-25231a1248ab.jpg https://dev.to/sagarrana25280 en Sagar Rana Sun, 11 Oct 2026 16:46:21 +0000 https://dev.to/sagarrana25280/garden-planner-open-source-ai-that-tells-you-what-to-plant-this-week-2djo https://dev.to/sagarrana25280/garden-planner-open-source-ai-that-tells-you-what-to-plant-this-week-2djo <h2> What I Built </h2> <p>A simple Garden Planner that tells users what vegetables, herbs, and flowers to plant this week based on their city and current month. Built with Google's open-weight <strong>Gemma 4 31B</strong> model.</p> <h2> The Problem </h2> <p>I live in Sunwal, Nepal. Every season I wonder: "What should I plant right now?" Most gardening apps are US-focused, need internet, or cost money. I wanted something free, private, and local.</p> <h2> Demo </h2> <p><strong>Input:</strong> City = Sunwal, Month = October</p> <p><strong>Output:</strong></p> <ul> <li>Leafy Greens: spinach, mustard greens (rayo), fenugreek (methi)</li> <li>Root Vegetables: carrots, radishes</li> <li>Cool-Season Veggies: cauliflower, cabbage, broccoli</li> <li>Legumes: garden peas</li> <li>Flowers: marigolds (sayapatri), petunias</li> </ul> <p>It even suggested Nepal-specific crops — that's the power of open models trained on diverse data.</p> <h2> How I Built It </h2> <ol> <li>Got a free API key from Google AI Studio</li> <li>Wrote a 30-line Python script using <code>requests</code> </li> <li>Called Gemma 4 via the Gemini API</li> <li>Used a prompt that asks for 5 bullet points</li> </ol> <h2> Why Open-Source AI Mattered </h2> <ul> <li> <strong>Free</strong> — no cost to run, no paid API tier</li> <li> <strong>Private</strong> — my location and garden data stay with me</li> <li> <strong>Swappable</strong> — I can switch to any open model (Gemma, Llama, Mistral) without rewriting code</li> <li> <strong>Local-first future</strong> — one day I can run this on my laptop with no internet at all</li> </ul> <p>A closed AI API would have cost money, locked me into one provider, and sent my location data to a server I don't control.</p> <h2> What's Next </h2> <p>Add frost-date logic per city, support Nepali language output, and run Gemma locally with Ollama.</p> devchallenge hf26challenge Sagar Rana Sun, 11 Oct 2026 16:29:37 +0000 https://dev.to/sagarrana25280/garden-planner-open-source-ai-that-tells-you-what-to-plant-this-week-4gmm https://dev.to/sagarrana25280/garden-planner-open-source-ai-that-tells-you-what-to-plant-this-week-4gmm <h2> What I Built </h2> <p>A simple Garden Planner that tells users what vegetables, herbs, and flowers to plant this week based on their city and current month. Built with Google's open-weight <strong>Gemma 4 31B</strong> model.</p> <h2> The Problem </h2> <p>I live in Sunwal, Nepal. Every season I wonder: "What should I plant right now?" Most gardening apps are US-focused, need internet, or cost money. I wanted something free, private, and local.</p> <h2> Demo </h2> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/PASTE_YOUR_SCREENSHOT_HERE" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/PASTE_YOUR_SCREENSHOT_HERE" alt="Garden Planner output" width="800" height="400"></a></p> <p><strong>Input:</strong> City = Sunwal, Month = October</p> <p><strong>Output:</strong></p> <ul> <li>Leafy Greens: spinach, mustard greens (rayo), fenugreek (methi)</li> <li>Root Vegetables: carrots, radishes</li> <li>Cool-Season Veggies: cauliflower, cabbage, broccoli</li> <li>Legumes: garden peas</li> <li>Flowers: marigolds (sayapatri), petunias</li> </ul> <p>It even suggested Nepal-specific crops — that's the power of open models trained on diverse data.</p> <h2> How I Built It </h2> <ol> <li>Got a free API key from Google AI Studio</li> <li>Wrote a 30-line Python script using <code>requests</code> </li> <li>Called Gemma 4 via the Gemini API</li> <li>Used a prompt that asks for 5 bullet points</li> </ol> <h2> Why Open-Source AI Mattered </h2> <ul> <li> <strong>Free</strong> — no cost to run, no paid API tier</li> <li> <strong>Private</strong> — my location and garden data stay with me</li> <li> <strong>Swappable</strong> — I can switch to any open model (Gemma, Llama, Mistral) without rewriting code</li> <li> <strong>Local-first future</strong> — one day I can run this on my laptop with no internet at all</li> </ul> <p>A closed AI API would have cost money, locked me into one provider, and sent my location data to a server I don't control.</p> <h2> What's Next </h2> <p>Add frost-date logic per city, support Nepali language output, and run Gemma locally with Ollama.</p> <h1> devchallenge #hf26challenge </h1> ai opensource software Sagar Rana Sun, 04 Oct 2026 16:16:00 +0000 https://dev.to/sagarrana25280/hi-world-of-learner-13mm https://dev.to/sagarrana25280/hi-world-of-learner-13mm <p>i am in my tech learning journey happy to be part of hacktoberfest</p>