Verdantra: An AI-Powered Field Journal That Gets You Outdoors 🌿
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built 🌿 Verdantra — Look closer outside. Verdantra is an open-source, AI-powered botanical field journal designed to encourage people to step away from their screens and explore the natural world. The idea is simple: take a photo of a leaf, plant, rock, puddle, or another outdoor subject, and use AI to…
Verdantra is an open-source AI-powered field journal designed to inspire people to venture outdoors and observe nature. The application allows users to upload photos of plants, rocks, puddles, or other natural elements, and then utilizes AI to analyze the image and provide information about the observed features. Key features of Verdantra include photo-based observations, visible evidence descriptions, honest uncertainty, safe mini-experiments, personal field journaling, and both online and offline AI modes.
The project's primary goal is to encourage curiosity about the real world, rather than replacing users' own observations. The application is built on a modern web stack, featuring React, TypeScript, Vite, and Tailwind CSS for the frontend, and Python and FastAPI for the backend. The AI integration supports both online and offline modes, using Google's Gemini API for online mode and the Gemma 4 E2B model through Ollama for offline use.
The AI emphasizes photo-grounded evidence, plain language, explicit uncertainty, and safe observation activities.
Verdantra is part of the Hacktoberfest Open-Source AI Challenge, focusing on open-source AI tools that make nature exploration accessible without requiring expensive hardware or a single online AI service. The project is built around the principle of open innovation, which allows developers to inspect, learn from, improve, and adapt the application for their own communities.
The code is available on GitHub, and the setup instructions detail how to run the backend and frontend locally, configure the AI provider, and test the application.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
