Urgent.News

What's breaking now, across thousands of outlets.

AI

TerraAI: Touch Grass โ€” An Open-Source AI That Turns Screen Time into Green Time

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Demo Code How I Built It Why Does Open Innovation Matter? My Agent Session Prize Categories This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built ๐ŸŒฟ TerraAI โ€” Touch Grass: Less Screen Time, More Green Time I built TerraAI , a web-based outdoorโ€ฆ

TerraAI is a web-based outdoor activity planner designed to encourage people to spend less time on their screens and more time outdoors. The project, submitted as part of the Hacktoberfest Open-Source AI Challenge Week 1, aims to promote mindful outdoor experiences.

TerraAI suggests activities such as mindful walking, gardening, birdwatching, and taking a break to appreciate nature. Users can select activities based on their current mood, available time, and personal interests. The planner offers light and dark themes for user convenience.

The project was built using HTML, CSS, and JavaScript, keeping the code lightweight and easily accessible through a web browser. It utilizes Transformers.js and an open-weight model from the Hugging Face ecosystem for AI integration. In case the AI model fails to load, a built-in recommendation system provides alternative outdoor activities.

The project is hosted on GitHub Pages, allowing users to access it via a public link. While the current version is a prototype, the AI model integration is experimental and requires an internet connection to download necessary files. The fallback recommendations do not require an AI model.

Open innovation plays a significant role in TerraAI's development, offering several advantages. It is more accessible for beginners, providing flexibility in model experimentation, reducing infrastructure requirements, offering control over the user experience, and promoting technology with a real-world purpose. Despite the limitations of open-weight models, this approach allows for exploration and learning about the technology involved.

Written by urgent.news from Dev.to's reporting โ€” not their text. Machine-written โ€” may contain errors; check the original before relying on it.

Read the original at dev.to โ†’

More in AI

Explora โ€” A Nature Journal Powered by Local AI

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built What if AI could help us spend less time staring at screens and more time noticing the world aroundโ€ฆ

  • Explora is a nature-walk journal powered by local AI model Gemma
  • Users can review AI suggestions, correct them, or leave discoveries unidentified
  • Project emphasizes curiosity, personal connection, and privacy-conscious image handling

๐ŸŒฟ Nature Buddy AI

๐ŸŒฟ Nature Buddy AI: Your AI Companion for Getting Outside What I Built Nature Buddy AI is an open-source AI-powered nature companion built for the Hacktoberfest Week 1 โ€œTouch Grassโ€ challenge.

StrollerPulse: The Screen-Free Shock & Terrain Watchdog Powered by Prior Labs TabPFN

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built When we take an infant out in a stroller or lace up our running shoes to head outdoors, mappingโ€ฆ

  • StrollerPulse monitors strollers and wheelchairs using smartphone sensors
  • Analyzes data with Prior Labs TabPFN for real-time voice cues
  • Screen-free design encourages sensor-based awareness over smartphones

Speaker Labels Burned a Full Hour of Compute and Returned Nothing. One Voice Print Per Phrase Fixed It

I run a visa agency in Bali. The part of my work that has nothing to do with visas is building Actors on Apify, and one of them is a transcriber: you give it an audio or video URL, it runs Whisperโ€ฆ

  • Speaker embeddings computed 10 times per second, inefficient for long audio
  • Updated actor focused on embedding speech, segmented audio at pauses
  • Compute usage reduced to 0.24 units, successful transcription achieved

Hephaestus: Local-First, Open-Source AI Agents That Train ML Models While You Go Outside

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Hephaestus is a local-first, autonomous coordinator for machine learning pipelines.

  • Hephaestus is an open-source AI agent for streamlining ML workflows.
  • Platform automates research, data collection, code writing, training, and debugging.
  • Local operation keeps sensitive data secure while running on CPUs/GPUs.

More from Sunday 11 October โ†’