Asteroid: How I built a Comet Browser Clone using Streamlit and TavilySearch — Part 1
Last Updated on October 7, 2025 by Editorial Team
Author(s): Dwaipayan Bandyopadhyay
Originally published on Towards AI.
Asteroid: How I built a Comet Browser Clone using Streamlit and TavilySearch — Part 1
We are all familiar with Perplexity AI and their popular product, Comet Browser, which has revolutionised how we surf the internet. After using that hands-on, I got an idea, I wanted to replicate the same (well, not the entire backend, but how they display the results to the users). In this article, I will walk through the simple approach I took to build a simple clone of the Comet Browser (This will be a 2-part story, as in the next part, I will make that better by integrating a Chatbot logic just like the Browser)
The article outlines the author’s journey in replicating the functionality of Comet Browser using Streamlit and TavilySearch. It begins with a prerequisite understanding of Python and Streamlit, followed by an explanation of how the Comet Browser operates by answering user queries through three sections: Assistant, Sources, and Images. The author provides a step-by-step guide on creating an account with Tavily for API access and the coding framework necessary to build the application, culminating in an emphasis on upcoming improvements and the importance of visual outputs.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.
Related posts
Recent Posts
