{"slug": "my-hacktoberfest-journey-building-an-ai-that-touches-grass-so-i-don-t-have-to", "title": "My Hacktoberfest Journey: Building an AI that touches grass so I don't have to", "summary": "A developer built the Offline Nature Identifier, an open-source tool that runs entirely on a laptop without a cell signal, using Ollama and LLaVA for local vision AI to identify plants and animals. The project, created for the Hacktoberfest \"Touch Grass\" challenge, was tested with Wi-Fi disabled and successfully identified a local bird while also issuing a wildlife safety warning. The developer deployed a landing page on Render and plans to use Tinker to fine-tune the model on regional bird species.", "body_md": "Hacktoberfest is all about open-source collaboration. When I saw the \"Touch Grass\" challenge prompt, I knew I had to build something that gets people away from their screens.\n\nI present to you: The Offline Nature Identifier.\n\nThe Idea-\n\nI wanted a tool that hikers, birdwatchers, and gardeners could use without a cell signal. A tool that runs entirely on your laptop, using open-source AI.\n\nHow I Built It (And The Tools I Used)\n\nOllama + LLaVA: I used these to handle the local vision AI. It identifies plants and animals right on your machine.\n\nBackboard: I used my Backboard credits to review my Python code and make it more efficient.\n\nRender: I used Render to deploy a simple static site for the project, making it accessible to everyone.\n\nTinker: In the future, I plan to use Tinker to fine-tune the model on regional bird species.\n\nThe \"Aha!\" Moment\n\nThe best part was testing it. I turned off my Wi-Fi, loaded a picture of a local bird, and ran my script. The AI successfully identified the bird and gave me a safety warning about observing wildlife from a distance. It was incredibly rewarding to see open-source AI working flawlessly offline.\n\nWhy Open-Source AI is Essential\n\nClosed AI keeps us tied to the cloud. Open-source AI, like the models I used here, gives power back to the developer. It allows us to build tools that are private, fast, and work anywhere on Earth.\n\nSee the Project:\n\nI deployed the landing page on Render: \n\n[[https://touch-grass-ai.onrender.com](https://touch-grass-ai.onrender.com)]", "url": "https://wpnews.pro/news/my-hacktoberfest-journey-building-an-ai-that-touches-grass-so-i-don-t-have-to", "canonical_source": "https://dev.to/_sakshi_68gi/my-hacktoberfest-journey-building-an-ai-that-touches-grass-so-i-dont-have-to-p38", "published_at": "2026-10-11 14:55:54+00:00", "updated_at": "2026-10-11 14:56:33.307509+00:00", "lang": "en", "topics": ["artificial-intelligence", "computer-vision", "ai-tools", "generative-ai"], "entities": ["Ollama", "LLaVA", "Backboard", "Render", "Tinker", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/my-hacktoberfest-journey-building-an-ai-that-touches-grass-so-i-don-t-have-to", "markdown": "https://wpnews.pro/news/my-hacktoberfest-journey-building-an-ai-that-touches-grass-so-i-don-t-have-to.md", "text": "https://wpnews.pro/news/my-hacktoberfest-journey-building-an-ai-that-touches-grass-so-i-don-t-have-to.txt", "jsonld": "https://wpnews.pro/news/my-hacktoberfest-journey-building-an-ai-that-touches-grass-so-i-don-t-have-to.jsonld"}}