An AI-powered travel planning application that uses Gemini LLM and CrewAI to automate trip planning with multiple specialized AI agents. This project demonstrates agentic AI collaboration to search flights, find hotels, and generate personalized travel itineraries.

Multi-Agent AI Travel Planner

An agentic AI travel planning application using Gemini LLM and CrewAI framework. This project demonstrates how AI agents collaborate to streamline the travel planning process - retrieving real-time flight and hotel data, analyzing options, and generating personalized itineraries.

Demo

Overview

This project demonstrates how to build a multi-agent system where specialized AI agents work together to create comprehensive travel plans. Instead of manually searching across multiple platforms, this application automates the process through intelligent AI collaboration.

The system leverages:

• Gemini 2.0 LLM: Powers the intelligence behind each agent
• CrewAI: Coordinates the multi-agent workflow
• SerpAPI: Retrieves real-time flight and hotel data
• FastAPI: Handles backend API endpoints
• Streamlit: Provides a user-friendly interface

Key Features

1. Flight Search Automation

• Retrieves real-time flight data from Google Flights via SerpAPI
• Filters flights based on price, layovers, and travel time
• AI recommends the best flight based on cost-effectiveness and convenience

2. Hotel Recommendations

• Searches real-time hotel availability from Google Hotels
• Filters based on location, budget, amenities, and user ratings
• AI suggests the best hotel by analyzing factors like proximity to key locations

3. AI-Powered Analysis & Recommendations

• Gemini LLM-powered AI agent evaluates travel options
• Uses CrewAI to coordinate multiple AI agents for better decision-making
• AI explains its recommendation logic for flights and hotels

4. Dynamic Itinerary Generation

• AI builds a structured travel plan based on flight and hotel bookings
• Generates a day-by-day itinerary with must-visit attractions, restaurant recommendations, and local transportation options

5. User-Friendly Inter