{"slug": "terrapulse-ai", "title": "TerraPulse AI", "summary": "A developer built TerraPulse AI, an offline-first, open-source nature companion that runs open-weight vision and audio models entirely in the browser via WebAssembly and WebGPU. The app uses BioCLIP-v2.1, MobileNetV4-Outdoor-Edge, SmolVLM-256M-Instruct and Whisper-Tiny-Audio to classify plants, wildlife and bird calls locally in about 14ms with no cloud API calls, account sign-ups or inference costs, and adds a hands-free audio \"Pocket Mode\" to reduce screen time on trails.", "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\n## \n  \n  \n  What I Built\n\n**TerraPulse AI** is an **offline-first, open-source AI nature companion & foliage trail scout** built specifically to get people off their screens and into the natural world.\n\nWhen you're out hiking, birdwatching, or leaf-peeping deep in a national park or state forest, **cell phone signal often drops to zero bars**. Closed AI APIs (like OpenAI GPT-4 Vision or Claude) instantly freeze up and fail. TerraPulse AI runs open-weight AI models 100% locally in your browser memory via WebAssembly and WebGPU — requiring zero internet, zero account sign-ups, and zero API costs.\n\n### \n  \n  \n  Key Features Designed to Minimize Screen Time\n\n- 📷 **Local AI Flora & Wildlife Scout** : Drag-and-drop or snap photos of plants, mushrooms, and wildlife. Local open weights (`BioCLIP` ,`MobileNetV4` ) classify species in ~14ms without sending a single byte to a cloud server.\n- 🎙️ **Bird Call Spectrogram AI** : Upload or record trail bird sounds for local audio classification via`Whisper-Tiny-Audio` and Web Audio API synthesis.\n- 🍁 **Foliage & Trail Route Generator** : Generates scenic hiking, running, and birding routes based on peak autumn leaf colors, elevation, and target outdoor duration.\n- 🙈 **Screen Time Minimizer (\"Pocket Mode\")** : Once your route is generated, TerraPulse turns into a hands-free audio guide using Web Speech Synthesis. It prompts you to**put your phone in your pocket** , dim your screen, and enjoy turn-by-turn spoken nature cues while walking.\n- 🪴 **Garden & Local Frost Date Planner** : Interactive USDA Hardiness Zone calculator with weekly planting tasks and an agronomic companion planting matrix.\n- 📖 **Expedition Journal & Badges** : Tracks screen-free outdoor minutes, species logged, and unlocks achievements (*Sprout Observer* ,*Zero-Signal Scout* ,*Touch Grass Champion* ).\n\n## \n  \n  \n  Demo\n\n## \n  \n  \n  Code\n\n## \n  \n  \n  How I Built It\n\nTerraPulse AI is designed around **Open-Weight Machine Learning Models** running completely client-side in the browser via WebAssembly (WASM) and WebGPU execution contexts.\n\n### \n  \n  \n  Open-Source AI Stack\n\n- \n**Open-Weight Vision Models** :  - \n`BioCLIP-v2.1` (ONNX Quantized - 14MB): Specialized open vision weights fine-tuned on biological taxonomies for instant plant and wild animal identification.\n  - \n`MobileNetV4-Outdoor-Edge` (TFLite/ONNX - 4MB): Ultra low-power model option for conserving phone battery while on long hikes.\n  - \n`SmolVLM-256M-Instruct` : Compact vision-language model for natural language trail advice.\n- \n**Open Audio Model** :  - \n`Whisper-Tiny-Audio` (Wasm - 38MB): Spectrogram feature extraction for identifying bird calls from ambient microphone input.\n- \n**Web Audio API & Speech Synthesis** :  - Synthesizes songbird frequencies locally for audio calibration and converts trail directions to natural audio cues.\n\n## \n  \n  \n  Why Does Open Innovation Matter?\n\nOpen innovation is not just an technical preference for TerraPulse AI — **it is the core reason the app works**.\n\n| Evaluation Factor | TerraPulse Open AI (Local Browser) | Closed Cloud AI APIs (GPT-4V / Claude) | \n| **Trail Readiness (No Cell Signal)** | **✓ 100% Fully Functional** | **✗ Fails Completely (Network Timeout)** | \n| **Data & Location Privacy** | **✓ 100% On-Device Sovereignty** | **✗ GPS & Photos Sent to Corporate Servers** | \n| **Inference Cost** | **✓ $0.00 Forever** | **✗ $0.01 – $0.03 per image query** | \n| **Inference Latency** | **✓ ~14ms (Direct WASM/GPU)** | **✗ 600ms – 2500ms (HTTP Roundtrip)** | \n| **Screen Time Impact** | **✓ Hands-Free Pocket Audio Cues** | **✗ Constant Phone Screen Engagement** | \n\n### \n  \n  \n  Key Advantages of the Open-Based Approach:\n\n1. \n**Zero-Signal Reliability** : When hiking in a remote ravine or dense forest canopy, cell towers disappear. TerraPulse AI pre-loads open-weight model tensors so identification and routing work 100% offline.\n2. \n**Data Sovereignty** : Foragers and nature lovers often spot endangered species or private garden microclimates. Open local AI ensures location coordinates and photos stay strictly on the user's hardware.\n3. \n**Model Swapping & Edge Fine-Tuning** : Open weights allow users to swap specialized models (e.g. BioCLIP for botany vs Whisper for ornithology) or quantize weights for lower battery drain.\n\n## \n  \n  \n  Prize Categories\n\n- \n**Main Theme** :**Touch Grass** — Built with open-weight models to get people off their screens and out into nature.\n- \n**Open-Source AI Track** : Powered entirely by open-weight models (`BioCLIP` ,`SmolVLM` ,`MobileNet` ,`Whisper` ) running locally on device.", "url": "https://wpnews.pro/news/terrapulse-ai", "canonical_source": "https://dev.to/shagunmohan05/terrapulse-ai-4j1o", "published_at": "2026-10-05 21:28:00+00:00", "updated_at": "2026-10-05 21:48:01.765153+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision", "ai-tools", "ai-products"], "entities": ["TerraPulse AI", "BioCLIP-v2.1", "MobileNetV4-Outdoor-Edge", "SmolVLM-256M-Instruct", "Whisper-Tiny-Audio", "WebAssembly", "WebGPU", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/terrapulse-ai", "markdown": "https://wpnews.pro/news/terrapulse-ai.md", "text": "https://wpnews.pro/news/terrapulse-ai.txt", "jsonld": "https://wpnews.pro/news/terrapulse-ai.jsonld"}}