Khoj: Step Outside With a Question, Come Back With a Story
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass Khoj (खोज) — Don't Follow the Map. Follow Your Curiosity. What I Built Khoj is an open-source, offline-first AI exploration companion that turns a walk around your city into a curiosity-driven adventure. It's easy to spend hours exploring a city through a screen without actually experiencing the world around…
Khoj is an open-source project that turns city walks into curiosity-driven adventures. It encourages users to step outside their screens and engage with the world around them. Starting with Mumbai, Khoj provides curiosity-driven missions, lets users record their observations, and helps turn those notes into a personal field journal. The app is designed for the Hacktoberfest 2026 Open-Source AI Challenge, Week 1: Touch Grass.
Khoj is a companion that doesn't tell users where to go, but rather gives them reasons to look around. It offers offline-first functionality, meaning it works even when connectivity is unreliable. The app uses a service worker to cache its app shell and static assets, and browser-side storage to preserve the user's active exploration session and observations.
Khoj is built with React, Vite, and Tailwind CSS for the frontend, Python and FastAPI for the backend, SQLite and browser-side storage for data storage, and Gemma 3 4B through Ollama for local AI inference. The app is organized in a way that allows different parts of the experience, such as exploration, city knowledge, AI mission generation, and observation-based journaling, to evolve independently.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.