DEV Community

Cover image for Build a Deep Research AI agent using Next.js, the Vercel AI SDK, and multiple LLMs, including Gemini and Deepseek.
CodeBucks
CodeBucks

Posted on

3 1 1

Build a Deep Research AI agent using Next.js, the Vercel AI SDK, and multiple LLMs, including Gemini and Deepseek.

#ai #nextjs #webdev #tutorial

I have built an open source Deep Research AI agent like Gemini or ChatGPT. Using Next.js, Vercel AI SDK, and Exa Search API, It generates follow-up questions, crafts optimal search queries, and compiles comprehensive research reports.

Using open router it is using multiple LLMs for different stages. At the last stage I have used gemini 2.0 reasoning model to generate comprehensive report based on the collected data from web search.

Check out the tutorial👇🏻

Let me know your thoughts, and feel free give star on the github repo.

Top comments (0)

Redis
 Promoted

Redis image

Short-term memory for faster
AI agents

AI agents struggle with latency and context switching. Redis fixes it with a fast, in-memory layer for short-term context—plus native support for vectors and semi-structured data to keep real-time workflows on track.

Start building

👋 Kindness is contagious

Sign in to DEV to enjoy its full potential—unlock a customized interface with dark mode, personal reading preferences, and more.

Okay