{"slug": "touchgrass-ai-an-open-weight-ai-that-gets-you-off-the-screen-and-into-the-real", "title": "TouchGrass AI — An Open-Weight AI That Gets You Off the Screen and Into the Real World", "summary": "A developer built TouchGrass AI, an open-source web app that uses open-weight models via Hugging Face Inference Providers to generate personalized outdoor missions and analyze user-uploaded nature photos, aiming to push people off their screens and outside. The project pairs a JavaScript frontend with a Node.js/Express backend that proxies the Hugging Face API token, using openai/gpt-oss-120b for text and Qwen/Qwen2.5-VL-3B-Instruct for vision. Its stated philosophy is that \"the best AI interaction is the one that gets you to stop using the AI.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass](https://dev.to/challenges/hacktoberfest-week1-2026-10-05)*\n\nI built **TouchGrass AI**, an AI-powered outdoor adventure companion designed to turn screen time into real-world activity.\n\nThe idea is simple: instead of keeping users inside an AI chat, the AI gives them a reason to **put the phone down and go outside**.\n\nUsers choose how much time they have, their environment, their mood, and what kind of experience they want. TouchGrass AI then generates a personalized outdoor mission, such as exploring nature, taking a short walk, observing plants or birds, or completing a small outdoor challenge.\n\nThe website also includes:\n\nThe target audience is anyone who spends too much time on screens and needs a simple push to get outside.\n\nThe core philosophy is:\n\n**The best AI interaction is the one that gets you to stop using the AI.**\n\n**Live Website:**\n\n[https://ayushkasaudhan957-eng.github.io/TouchGrass-AI/](https://ayushkasaudhan957-eng.github.io/TouchGrass-AI/)\n\nThe website is deployed and can be used directly in the browser.\n\n**GitHub Repository:**\n\n[https://github.com/ayushkasaudhan957-eng/TouchGrass-AI](https://github.com/ayushkasaudhan957-eng/TouchGrass-AI)\n\nThe complete source code is open and available in the repository.\n\nTouchGrass AI is built around **open-weight AI models** accessed through Hugging Face Inference Providers.\n\nFor text generation, I used:\n\n`openai/gpt-oss-120b`)` Qwen/Qwen2.5-VL-3B-Instruct`) for vision-based image analysis\nHugging Face Inference Providers provides access to open models through an OpenAI-compatible chat-completion endpoint, allowing the application to use hosted inference without requiring users to download a local model.\n\n```\nUser\n  ↓\nTouchGrass AI Website\n  ↓\nHTML + CSS + JavaScript\n  ↓\nNode.js / Express Backend\n  ↓\nHugging Face Inference Providers\n  ↓\nOpen-Weight AI Models\n  ↓\nPersonalized Outdoor Mission / Nature Analysis\n```\n\nThe frontend handles the user experience, mission builder, timer, XP, journal and image upload.\n\nThe backend acts as a secure AI proxy so that the Hugging Face API token is not exposed in the browser.\n\nFor mission generation, the user's preferences are converted into a structured prompt and sent to the open-weight language model.\n\nFor the nature discovery feature, an uploaded image is sent to a vision-language model which analyzes what is visible and provides an AI-generated observation.\n\nI intentionally chose hosted inference instead of requiring users to install Ollama, LM Studio, or download large models. This makes the project much easier to try while still keeping open-weight models at the core of the AI functionality.\n\nOpen innovation makes this project possible because the AI layer is not loc", "url": "https://wpnews.pro/news/touchgrass-ai-an-open-weight-ai-that-gets-you-off-the-screen-and-into-the-real", "canonical_source": "https://dev.to/ayush_kasaudhan_01/touchgrass-ai-an-open-weight-ai-that-gets-you-off-the-screen-and-into-the-real-world-3c0d", "published_at": "2026-10-09 11:11:45+00:00", "updated_at": "2026-10-09 11:21:29.275323+00:00", "lang": "en", "topics": ["ai-tools", "generative-ai", "large-language-models", "computer-vision", "ai-products"], "entities": ["TouchGrass AI", "Hugging Face", "openai/gpt-oss-120b", "Qwen/Qwen2.5-VL-3B-Instruct", "Node.js", "Express", "GitHub", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/touchgrass-ai-an-open-weight-ai-that-gets-you-off-the-screen-and-into-the-real", "markdown": "https://wpnews.pro/news/touchgrass-ai-an-open-weight-ai-that-gets-you-off-the-screen-and-into-the-real.md", "text": "https://wpnews.pro/news/touchgrass-ai-an-open-weight-ai-that-gets-you-off-the-screen-and-into-the-real.txt", "jsonld": "https://wpnews.pro/news/touchgrass-ai-an-open-weight-ai-that-gets-you-off-the-screen-and-into-the-real.jsonld"}}