A sophisticated AI-powered negotiation platform that simulates real-world negotiations using multiple intelligent agents. Built with Google's Gemini AI, this platform demonstrates advanced negotiation strategies, autonomous decision-making, and dynamic price optimization.
-
Multi-Agent System
- 🤝 Buyer Agent: Strategic price negotiation with learning capabilities
- 💼 Seller Agent: Adaptive pricing based on market conditions
- ⚖️ Mediator Agent: Facilitates negotiations and suggests compromises
-
Real-Time Negotiation
- 📊 Live negotiation progress tracking
- 💬 Dynamic message exchange between agents
- 🎯 Automatic price convergence detection
-
Advanced Analytics
- 📈 Negotiation efficiency metrics
- 🎯 Fair value index calculation
- 🧮 Complexity score assessment
- 📋 Detailed transaction history
-
Modern UI/UX
- 🎨 Clean, intuitive interface
- 📱 Fully responsive design
- ✨ Smooth animations and transitions
- 🌓 Light/Dark mode support
-
Real-Time Updates
- ⚡ Live negotiation progress
- 🔄 Automatic status updates
- 📊 Dynamic price tracking
-
Backend
- 🐍 Python 3.9+
- 🌶️ Flask Web Framework
- 🤖 Google Gemini AI API
- 🗄️ SQLite Database
-
Frontend
- 🎨 Modern CSS with Custom Properties
- 📱 Responsive Design
- 🎭 Custom Animations
- ⚡ Vanilla JavaScript
- Python 3.9 or higher
- Google Gemini API key
- Modern web browser
-
Clone the repository:
git clone https://github.com/yourusername/negotiation-multiagent.git cd negotiation-multiagent -
Run the setup script:
- Windows:
setup.bat - Unix/Mac:
./setup.sh
- Windows:
-
Configure your environment:
copy .env.example .env # Edit .env and add your Gemini API key -
Start the application:
- Windows:
run.bat - Unix/Mac:
./run.sh
- Windows:
-
Open your browser and navigate to:
http://localhost:5000
-
Initialization
- User inputs item details and price ranges
- System initializes three AI agents: buyer, seller, and mediator
-
Negotiation Rounds
- Buyer makes initial offer
- Seller responds with counter-offer
- Mediator intervenes periodically to facilitate agreement
- Process continues until agreement or maximum rounds reached
-
Agreement Detection
- System automatically detects when agents reach agreement
- Validates final price against initial constraints
- Records successful negotiations in database
- Analyzes item value and market conditions
- Implements strategic bidding patterns
- Adapts offers based on seller responses
- Learns from negotiation history
- Evaluates market position and item worth
- Employs dynamic pricing strategies
- Considers buyer's negotiation pattern
- Maintains profit margins while being flexible
- Monitors negotiation progress
- Identifies deadlock situations
- Suggests compromises based on both positions
- Helps optimize for mutual benefit
- Negotiation Speed: Rounds to agreement
- Price Convergence: Rate of offer adjustments
- Success Rate: Percentage of successful negotiations
- Market value analysis
- Price trend correlation
- Historical transaction comparison
- Number of rounds required
- Price movement patterns
- Intervention frequency
- Animated progress indicators
- Live message updates
- Dynamic price tracking
- Negotiation timeline
- Price history graphs
- Status indicators
- Mobile-first approach
- Adaptive layouts
- Touch-friendly interfaces
- 🌐 Multi-language support
- 📊 Advanced analytics dashboard
- 🤝 Multi-party negotiations
- 🔄 Integration with real market data
- 🎯 Custom negotiation strategies
Contributions are welcome! Please read our Contributing Guidelines for details on our code of conduct and the process for submitting pull requests.
This project is licensed under the MIT License - see the LICENSE file for details.
- Google Gemini AI for providing the advanced language model
- Flask community for the excellent web framework
- All contributors who have helped shape this project
Made with ❤️ by hari7261