Wayfarer AI – Your Open-Source Travel Companion

Abhay Singh — Sat, 31 Oct 2026 09:15:34 +0000

Wayfarer — Travel Beyond the Ordinary 🌍

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

What I Built

I built Wayfarer, a modern travel discovery website designed to make exploring the world easier and more inspiring.

The idea behind Wayfarer is simple: travel should be about discovering experiences, not just searching for destinations.

The website allows users to:

Explore beautiful destinations around the world.
Search for destinations.
Filter places by travel style, including beaches, mountains, cities and culture.
Save favourite destinations.
Browse a responsive and modern travel interface.

I interpreted the Ghost in the Machine theme as an opportunity to explore how intelligent technology could make travel discovery more personal and meaningful.

Demo

Live Demo: https://abhay-code113.github.io/Wayfarer-AI-/

Local Demo: https://abhay-code113.github.io/Wayfarer-AI-/

Code

GitHub Repository: https://abhay-code113.github.io/Wayfarer-AI-/

The project is built using:

HTML5
CSS3
JavaScript

How I Built It

I developed Wayfarer using HTML, CSS and vanilla JavaScript.

HTML provides the website structure, CSS handles the responsive design and visual experience, and JavaScript powers destination searching, category filtering and favourite buttons.

The current version is a frontend prototype. Open-source AI integration is not yet implemented, so I am not claiming that an AI model or agent powers the existing application.

Why Does Open Innovation Matter?

Open innovation makes technology more accessible and gives developers the freedom to experiment, customize and build without depending entirely on closed platforms.

For a project like Wayfarer, an open-source AI travel assistant could eventually help users discover destinations, generate personalized itineraries and find experiences based on their interests.

Using open-weight models and local inference could also provide more control over user data, model customization and operating costs.

My Agent Session

Not available yet.

The Spirit of It

Travel is about the places we discover, the people we meet and the memories we create.

Wayfarer is my attempt to bring that feeling into a digital experience.

I want to build something that inspires people to explore beyond their usual destinations and discover places they might never have considered.

The world is bigger than our comfort zone. Let's explore it. 🌍

Prize Categories

Open-source AI integration is planned but not yet implemented. I will select the applicable partner categories once the AI component is complete.

TouchGrass AI: Turn a Few Free Minutes Into an Outdoor Adventure

Abhay Singh — Fri, 09 Oct 2026 11:22:20 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built

TouchGrass AI turns a nearby starting point, the time you have, and your mood into a short outdoor micro-adventure. It gives you three simple steps, then encourages you to put your phone away and go do them.
It’s for anyone who wants a quick reason to take a walk, explore a nearby park, or notice more of the nature around them.
Demo
Try TouchGrass AI
Code
View the source code on GitHub
How I Built It

I built TouchGrass AI with HTML, CSS, and JavaScript. It uses the open-source WebLLM runtime to run the open-weight Qwen2.5 1.5B Instruct model in the browser using WebGPU.
The user’s place, available time, and selected mood become a prompt for the model. It generates a short plan with a title, an introduction, and three steps. The first model download requires internet; after setup, inference runs locally in the browser.
Why Does Open Innovation Matter?
TouchGrass AI is meant to help people spend less time on screens, so I wanted the AI generation to work without sending their outing details to a hosted AI service. Local inference keeps the prompt on the user’s device and avoids needing an AI API key or paying per request.
Using open tools also makes the project easier to adapt: I can change the prompt, try a different supported model, and shape the guide around the experience I want to build.
My Agent Session
I don’t have a DevRelay session link to share.
Prize Categories
Open-Source AI Challenge — Touch Grass.

DEV Community: Abhay Singh