A powerful Python project implementing AI-driven Wordle solving strategies with multiple heuristics, batch performance testing, and interactive gameplay.

This project implements an AI-powered Wordle game solver capable of:

• Interactive Player vs AI gameplay
• AI vs AI comparisons
• Batch testing for heuristic performance
• Real-time strategy visualization

With multiple heuristics and solver strategies, this project provides insights into optimal word-guessing algorithms.

• 🧠 Advanced AI Solvers Supports Constraint-Based Problem (CBP) and A* Optimized Solver with multiple heuristics.

• 🎯 Heuristic Strategies Includes Entropy, Minimax, Expected Size, Hybrid, Positional, and Cached heuristics for optimal guessing.

• 📊 Batch Performance Testing Analyze solver efficiency over hundreds of secret words.

• 🖥️ Interactive UI Built with Gradio for a clean and user-friendly interface.

• 🏆 AI vs AI Comparison Test multiple solvers against the same word to identify the most efficient strategy.

# Clone the repository
git clone https://github.com/DishankVyas/AI-Wordle-Solver
cd ai-wordle

# Install dependencies
pip install -r requirements.txt

# Run the application
python wordle_ai.py

Note: Requires Python 3.9+ and the Gradio library.

Play against AI:

1. Select "CBP AI" or "A* AI".
2. Input your guess.
3. Observe AI's response in real time.

Batch Testing Example:

# Run batch analysis for 100 words
from batch_test import run_batch
run_batch('entropy', num_words=100)

Query Solver Efficiency:

# Compare heuristics
from heuristics import compare_solvers
compare_solvers(['entropy', 'minimax', 'hybrid'])

• Average guesses to solve a word
• Success/failure rates
• Time per guess
• Heuristic comparison charts

• Multiplayer Wordle challenges
• Difficulty levels for players
• AI learning via reinforcement learning
• Online leaderboard integration
• Enhanced analytics dashboards

• Dishank Vyas
• Krishna Shetty
• Pal Soni

Contributions are welcome!

1. Fork the repository.
2. Create a new feature branch:

   git checkout -b feature/your-feature-name

3. Commit your changes:

   git commit -m 'Add your feature'

4. Push to GitHub:

   git push origin feature/your-feature-name

5. Open a Pull Request 🙌