Your intelligent multi-agent travel companion for seamless trip planning

TravelMate AI revolutionizes travel planning through an intelligent multi-agent system that understands, learns, and adapts to your travel needs. Built with cutting-edge AI technology, it seamlessly orchestrates flight bookings, hotel reservations, destination exploration, and comprehensive trip coordination through natural conversations.

Our sophisticated multi-agent architecture employs specialized AI agents, each mastering specific travel domains while collaborating intelligently to deliver unified, context-aware travel solutions.

• Flight Agent: Advanced flight search, price tracking, and booking assistance
• Hotel Agent: Accommodation discovery with preference matching
• Destination Agent: Local insights, attractions, and cultural recommendations
• Team Coordinator: Orchestrates cross-agent collaboration for complex itineraries

• Contextual Memory: Maintains full conversation history across sessions
• Natural Language Processing: Understands complex, multi-part travel requests
• Thread Persistence: Seamless conversation continuity with client-side thread management

• Modular Architecture: Easy to extend with new agents and capabilities
• RESTful API: Clean endpoints for seamless integration
• LangGraph Framework: State-of-the-art agent orchestration and workflow management

• Framework: FastAPI (high-performance async Python web framework)
• AI/ML: LangChain + LangGraph (advanced agent orchestration)
• Language: Python

• Framework: React with TypeScript
• Styling: Tailwind CSS
• Type Safety: Full TypeScript implementation

• Version Control: Git with GitHub workflows
• Testing: Automated testing suite (coming soon)

• Python 3.8 or higher
• Node.js 16+ and npm
• Git

# Clone the repository
git clone https://github.com/aymen-000/travel-agent.git
cd travel-agent

# Setup Python environment
uv sync 
source .venv/bin/activate



# Start the development server
cd backend
uvicorn main:app --reload --host 0.0.0.0 --port 8000

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Start development server
npm run dev

Create a .env root for agents configuration :

# API Keys (obtain from respective providers)
AMADEUS_CLIENT_ID = ""
AMADEUS_CLIENT_SECRET = ""
FLIGHT_AGENT_MODEL_ID = ""
TOGETHER_API_KEY =""
HOTEL_AGENT_MODEL_ID = ""
TAVILY_API_KEY = ""

Create a .env.local in frontend root:

NEXT_PUBLIC_BACKEND_URL=http://127.0.0.1:8000 

{
  "query": "Find round-trip flights from NYC to Tokyo for 2 adults, departing June 15th",
  "thread_id": "uuid-v4-thread-identifier"
}

{
  "response": "I found several excellent flight options for your NYC to Tokyo trip...",
  "agent_id": "flights",
  "thread_id": "uuid-v4-thread-identifier",
  "timestamp": "2025-08-09T21:00:00Z",
}

• Car Rental Agent Integration

  • Vehicle search and comparison
  • Rental booking workflow
  • Insurance and addon management

• Enhanced Search Capabilities

  • Deep web research agent
  • Real-time price monitoring
  • Deal aggregation and alerts

• Advanced Personalization

  • User profile system with preferences
  • AI-driven recommendation engine
  • Travel history and pattern analysis
  • Budget optimization algorithms

• Infrastructure Improvements

  • Redis-based session management
  • Microservices architecture migration
  • Kubernetes deployment support
  • Comprehensive monitoring and logging

• Collaborative Intelligence

  • Multi-agent negotiation for complex bookings
  • Cross-platform integrations (Google Travel, Expedia, etc.)
  • Group travel coordination features
  • Real-time collaboration tools

• Next-Gen Features

  • AR/VR destination previews
  • Voice-based travel assistant
  • Blockchain-based loyalty system
  • Carbon footprint optimization

We welcome contributions from the community! TravelMate AI thrives on collaborative development and diverse perspectives.

1. Fork the Repository

   git fork https://github.com/aymen-000/travel_agent.git

2. Create a Feature Branch

   git checkout -b feature/amazing-new-feature

3. Make Your Changes

   • Follow our coding standards and conventions
   • Add tests for new functionality
   • Update documentation as needed

4. Submit a Pull Request

   • Provide a clear description of your changes
   • Reference any related issues
   • Ensure all tests pass

• Issues: Report bugs via GitHub Issues
• Discussions: Join our GitHub Discussions

We foster an inclusive, respectful environment where everyone can contribute meaningfully to advancing intelligent travel technology.

Made with ❤️ by Aimen

TravelMate AI represents a passion project combining artificial intelligence, travel industry expertise, and user-centered design. Built with dedication to solving real-world travel planning challenges through innovative technology.

"Travel opens minds, and AI makes it accessible to everyone." - Aimen

• GitHub: @aymen-000
• LinkedIn: [Profile](https://linkedin.com/in/aimen-profile

This project is licensed under the MIT License.

Special thanks to:

• LangChain Community for the powerful agent framework
• FastAPI Team for the exceptional web framework
• React Community for the robust frontend ecosystem
• Open Source Contributors who inspire and enable innovation

Current Version: v1.0.0-beta
Development Status: Active Development
Last Updated: August 2025