Skip to content

An AI-powered scouting assistant that turns raw GRID eSports data into actionable strategic reports, helping teams counter opponents instantly.

License

Notifications You must be signed in to change notification settings

LiwaaCoder/auto-scout

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Auto-Scout Banner

🚀 AUTO-SCOUT: Tactical Intelligence Unit

Python FastAPI Gemini AI Tailwind CSS Built with Junie License: MIT

The Next-Gen Esports Scouting Platform for Auto Scout Analytics


⚡ Overview

Auto-Scout is a cutting-edge tactical analysis tool designed to give esports teams a competitive edge. By combining real-time match data with Google Gemini's generative AI, Auto-Scout processes raw match history into actionable strategic insights, drafting recommendations, and player tendency reports—all presented in a high-fidelity Sci-Fi "Glassmorphism" HUD.

🎥 System Demo

Auto-Scout Demo

📸 Interface Preview

Full HUD View Strategic Report

🔥 Key Features

  • 🔎 Instant Opponent Scan: Input any pro player or team tag (e.g., Faker, T1, G2) to retrieve instant match analytics.
  • 🧠 AI-Powered Strategy: Uses Gemini 1.5 Flash to generate deep-dive scouting reports, identifying win conditions, weakness exploitation, and draft counters.
  • 📊 Real-Time Metrics: Visualizes Win Rate, KDA, Gold per Minute, and First Blood participation with reactive charts.
  • 🛡️ Champion Pool Detection: Automatically extracts and displays the most played champions from the last 5 games.
  • ✨ Pro-Level UX: A fully responsive, dark-mode specialized interface featuring neon glows, tactical fonts, and smooth animations.

🛠️ Tech Stack

Backend (The Brain)

  • FastAPI: High-performance async API framework.
  • Google Gemini API: For generating semantic scouting reports.
  • Pydantic: Robust data validation and settings management.

Frontend (The Face)

  • Vanilla JS + HTML5: Lightweight, no-build architecture.
  • Tailwind CSS: Utility-first styling for complex layouts.
  • Orbitron & Inter Fonts: For that signature "Esports" look.

🚀 Quick Start

1. Clone the Repository

git clone https://github.com/LiwaaCoder/auto-scout.git
cd auto-scout

2. Configure Environment

Create a .env file in the root directory and add your Gemini API key:

GEMINI_API_KEY=your_api_key_here

3. Install Dependencies

pip install -r backend/requirements.txt

4. Deploy the System

Start the backend analysis engine:

cd backend
uvicorn main:app --reload

Then, simply open index.html in your browser, or serve it:

# In a new terminal window
python -m http.server 3000

Visit http://localhost:3000 to access the HUD.


🔮 Future Roadmap

  • Live Draft Assistant: Real-time pick/ban recommendations during champion select.
  • Vision Mapping: Heatmaps for warding locations based on historical data.
  • Team Sync: Multiplayer lobby for coaches and analysts to view the same session.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.


Built with 💙 by Auto Scout Team

About

An AI-powered scouting assistant that turns raw GRID eSports data into actionable strategic reports, helping teams counter opponents instantly.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published