FoliageStride AI — Scenic Autumn Run & Park Route Explorer
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built FoliageStride AI is a scenic autumn run & park route builder built to solve a modern fitness irony: runners going outdoors just to stare at GPS screens, pace charts, and turn-by-turn prompts every 30 seconds. Instead of keeping runners glued to their devices, FoliageStride AI uses Google Gemma 2…
FoliageStride AI is an innovative AI-powered application aimed at transforming the way people enjoy outdoor runs. The primary goal of this project is to minimize the reliance on GPS screens during runs, a behavior that has become commonplace due to modern fitness trends. Instead, FoliageStride AI focuses on enhancing the runner's experience by generating scenic autumn routes based on user preferences, such as distance, desired scenery, terrain preference, and pacing style.
Upon launching the application, users can select their preferred distance, whether it's 2 km, 5 km, or 8 km, and choose the type of autumn scenery they wish to experience, such as maple and oak canopies, riverbank reflections, historic park perimeters, or hilltop ridges. Google Gemma 2, a local AI model integrated through Ollama, then utilizes this information to generate structured route details along with memorable physical landmarks, like The Century Red Oak Grove, Heron Creek Footbridge, or the Old Stone Wall, that runners can mentally commit to before starting their run.
One of the standout features of FoliageStride AI is its hands-free audio system. It employs the browser's native Web Audio API to create cadence chimes at kilometer milestones. This means runners can enjoy their run without constantly checking their devices, as the auditory cues guide them through their run. The visual representation of the run is achieved through SVG-based graphics that display the route and elevation profile, complete with visual markers for the important foliage and landmarks mentioned earlier.
In the event that the local Gemma 2 model is unavailable, FoliageStride AI ensures functionality through a deterministic fallback route-generation engine, maintaining usability even without a running local AI model. The Stride Journal, which tracks completed sessions and outdoor streaks, utilizes browser localStorage for offline functionality, eliminating the need for a cloud database.
The development of FoliageStride AI was an collaborative effort, facilitated by pairing with Google Antigravity. The agent assisted in various aspects of the project, including the responsive UI layout, autumn-themed visual design, SVG course elevation profile, structured JSON schema for the Gemma 2 prompting, hands-free Web Audio API synthesizer, and overall project structure. The final project was refined around the core concept of enabling runners to "touch grass" instead of constantly checking their screens.
The significance of this project lies in its alignment with the principles of open innovation and open-weight models like Google Gemma 2. These models are particularly valuable for outdoor and fitness applications, as they enable trail readiness with limited connectivity, enhance privacy by processing information locally rather than sending it to third-party servers, and avoid the cost associated with per-request cloud AI services.
By providing an AI-driven tool that enhances the outdoor running experience without sacrificing privacy or requiring constant internet access, FoliageStride AI stands out as a prime example of how open innovation can positively impact everyday activities.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
