In few hours, we designed a traval planning agent using HuggingFace’s library smolagents, integrated with DuckDuckgo for information retrieval and a browser tool for booking accommodations and activities. The agent can understand user preferences, search for relevant information, and make bookings autonomously. Main features include real-time web browsing, structured data extraction, multi-budget handling, and personalized itinerary generation. We achieved third-place in the hackathon.

Link to the github repository : [Here](https://github.com/charles-azam/hackathon-huggingface

)