Wanderlore: What if your next walk had a plot?
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass . The first time I tried to test my walking app properly, I couldn't even get it to find me. I was on my laptop, staring at another location timeout. I kept wondering what was wrong. How was I supposed to build a story that followed a walk if it couldn't tell where I was? Then I tried it on my phone. It…
This project, named Wanderlore, transforms a simple walk into an interactive story experience. You can choose from three genres - folklore, mystery, or fantasy - set the desired duration for your walk, and describe the weather conditions. Based on your choices, the platform generates a narration and visual elements to accompany your walk.
The core of Wanderlore is Gemma, an AI story engine. It maintains the narrative state across the walk, integrating your choices, genre, weather, and nearby locations if they are covered by the selected map pack. Each chapter builds upon your previous decisions and the current context, providing a unique narrative experience each time.
The storytelling is delivered through ElevenLabs, which provides high-quality voice narration. The voice is designed to be warm and engaging, encouraging you to continue listening.
Wanderlore relies on OpenStreetMap data for location-based storytelling. While the current version only covers central Lucknow, users can import GeoJSON packs for other areas. However, without matching nearby places, the story uses general surroundings.
The codebase is built using Python, FastAPI, and a responsive HTML/CSS/JavaScript frontend. It is released under the GPL-3.0 license, ensuring free use and modification. The story engine Gemma, along with the voice models, can also be run locally using Ollama or Kokoro, providing an option for offline use.
In essence, Wanderlore offers a novel way to explore the world around you, turning every walk into a personalized, interactive story.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
