WIldGuard AI

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

What I Built

WildGuard AI — AI-Powered Wildlife Exploration

WildGuard AI is an AI-powered wildlife application designed to help people identify wildlife, understand ecological risks, and learn more about the natural world.

The project uses a multi-agent architecture to handle different wildlife-related tasks, including species identification, geographic verification, risk assessment, ecological knowledge, and report generation.

The idea is to use AI to encourage people to explore nature, learn about wildlife, and develop a better understanding of the ecosystems around them.

Instead of keeping AI limited to screen-based activities, WildGuard AI aims to make it a useful companion for real-world wildlife exploration.

Demo

Try the live application:

https://satyakamspc.github.io/Wildguard-AI/

Code

GitHub repository:

https://github.com/satyakamspc/Wildguard-AI/

How I Built It

I built WildGuard AI using React, Django, Google ADK, and Gemini API.

The project follows a multi-agent architecture, with specialized agents responsible for different tasks:

• Species Identification: Identifies wildlife from available information.
• Geographic Verification: Evaluates whether a species is consistent with a reported location.
• Risk Assessment: Assesses potential wildlife-related risks.
• First Aid Generation: Provides relevant guidance for wildlife encounters.
• Ecological Knowledge: Explains species characteristics and their ecological significance.
• Report Generation: Organizes wildlife-related findings into structured reports.
• Agent Orchestration: Coordinates the different agents to complete tasks.

For this challenge, I am exploring how open-source AI models can make wildlife identification and nature exploration more accessible, flexible, and less dependent on proprietary AI services.

Why Does Open Innovation Matter?

Open innovation gives developers the freedom to experiment with AI models, inspect their behavior, and adapt them to specific use cases.

In wildlife applications, open-weight models offer opportunities for local inference, offline identification, and greater control over how observation data is processed.

They also allow developers to compare models, evaluate their performance on local wildlife species, and build applications without being permanently tied to a single AI provider.

My goal is to explore how open AI can support wildlife awareness and encourage people to connect with nature.

My Agent Session

No agent session attached.

Prize Categories

• Best Use of GitHub Copilot

This is an individual submission.