{"slug": "touchgrass-ai-go-outside-touch-grass", "title": "🌿 TouchGrass AI — Go Outside. Touch Grass.", "summary": "Developer Shirshak Nandy built TouchGrass AI, a local-first outdoor companion app that uses an open-weight Qwen model to generate structured outdoor missions with titles, durations, and task checklists. The React frontend and Flask backend run entirely locally through Hugging Face Transformers, avoiding paid AI APIs, with a fallback mission when generation fails. The project was created for the Open-Source AI / Touch Grass Challenge and is published on GitHub.", "body_md": "I built **TouchGrass AI**, a local-first AI outdoor companion that creates simple and fun outdoor missions.\n\nThe idea is simple: instead of using AI to keep people on a screen, **TouchGrass AI uses AI to encourage people to leave the screen and explore the real world.** 🌿\n\nThe app generates missions such as:\n\nUsers can start a mission, complete tasks using an interactive checklist, track their progress, and generate a new mission whenever they want.\n\nMost importantly, the AI runs **locally** using an open-weight model, so the project does not require a paid AI API.\n\n**Local Demo:**\n\nThe application runs locally with a React frontend and Flask backend.\n\nFrontend:\n\n`http://localhost:5173`\n\nBackend:\n\n`http://127.0.0.1:5000`\n\n**GitHub Repository:**\n\n[https://github.com/nandyshirshak-cloud/TouchGrass-AI](https://github.com/nandyshirshak-cloud/TouchGrass-AI)\n\nThe repository contains the complete frontend, backend, AI integration, and setup instructions.\n\nTouchGrass AI was built using:\n\nThe AI model runs locally through Hugging Face Transformers.\n\nThe basic flow is:\n\n**User → React Frontend → Flask Backend → Local Qwen AI → Outdoor Mission → User goes outside 🌿**\n\nThe backend asks the local model to generate a structured outdoor mission containing a title, duration, and tasks.\n\nThe frontend then displays the generated mission as an interactive checklist.\n\nI also added a fallback mission so the application can still provide an outdoor activity if AI generation fails.\n\nOpen innovation matters because powerful AI should not only be available through expensive closed APIs.\n\nWith open-weight models, developers can:\n\nTouchGrass AI is a small example of this idea.\n\nInstead of building another AI tool that encourages people to spend more time online, I wanted to use open AI technology for something very simple:\n\n**Use AI to help people spend less time with technology.**\n\nThe development process involved using AI-assisted coding to design the application, debug the React frontend, connect the Flask backend, integrate the local Qwen model, improve the mission-generation prompt, and prepare the project for open-source publication.\n\nOne of the interesting parts was getting the local model to return structured JSON containing:\n\nThis allowed the AI-generated content to be displayed directly inside the application.\n\nMost AI applications try to keep users engaged with a screen.\n\n**TouchGrass AI does the opposite.**\n\nThe screen is only used to receive the mission.\n\nAfter that, the user is encouraged to put the device down and complete the real-world activity.\n\n**Less screen. More world. 🌿**\n\nI would like to expand TouchGrass AI with:\n\nBuilt for the **Open-Source AI / Touch Grass Challenge**.\n\nThe project focuses on using open AI technology to encourage people to disconnect from their screens and interact with the physical world.\n\n**SHIRSHAK Nandy**\n\nGitHub:\n\n[https://github.com/nandyshirshak-cloud](https://github.com/nandyshirshak-cloud)\n\n🌿 **Less screen. More world.**\n\n**Go outside. Touch Grass.**", "url": "https://wpnews.pro/news/touchgrass-ai-go-outside-touch-grass", "canonical_source": "https://dev.to/shirshak_nandy_2cd2a85ce0/-touchgrass-ai-go-outside-touch-grass-18ei", "published_at": "2026-10-06 17:12:02+00:00", "updated_at": "2026-10-06 17:19:00.927887+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-tools", "large-language-models", "generative-ai"], "entities": ["TouchGrass AI", "Shirshak Nandy", "Qwen", "Hugging Face", "React", "Flask", "GitHub"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/touchgrass-ai-go-outside-touch-grass", "markdown": "https://wpnews.pro/news/touchgrass-ai-go-outside-touch-grass.md", "text": "https://wpnews.pro/news/touchgrass-ai-go-outside-touch-grass.txt", "jsonld": "https://wpnews.pro/news/touchgrass-ai-go-outside-touch-grass.jsonld"}}