A powerful Deep Research AI agent like Gemini or ChatGPT. Using Next.js, Vercel AI SDK, and Exa Search API, An intelligent system that generates follow-up questions, crafts optimal search queries, and compiles comprehensive research reports.

If you want to learn how to create it please follow below tutorial👇:
➡ Tutorial Link 💚: Deep research ai agent

If you are looking for old tutorial version please checkout this branch:
Tutorial Version (Old)

🎯 For customised solutions or deployment please contact: https://tally.so/r/wdlj0N

• 🔧 Fully Customizable Research Flow
• 🔍 Adaptive Search Queries
• ⚙️ Seamless LLM Integration
• 💼 Modular Components
• 🌐 Next.js & Vercel AI SDK
• ♻️ Iterative Research Loop

• Framework: Next.js 16 (App Router, Turbopack)
• Styling: Tailwind CSS v4, Shadcn UI
• AI Integration: Vercel AI SDK v6
• LLMs: GPT-4o, Gemini, Deepseek via OpenRouter
• Web Search: Exa Search API
• UI Components: Shadcn
• Language: TypeScript
• Package Manager: Bun

This branch has been migrated from the original tutorial stack to the latest versions. The runtime behaviour is the same — only the toolchain moved forward.

• Next.js 15 → 16 (Turbopack production builds, next lint removed)
• Vercel AI SDK 4 → 6 (generateObject replaced with generateText + Output.object(), useChat now uses DefaultChatTransport)
• @ai-sdk/react 1 → 3, @openrouter/ai-sdk-provider 0.4 → 2
• Zod 3 → 4, lucide-react 0.x → 1, react-syntax-highlighter 15 → 16
• ESLint config migrated to the native flat config from eslint-config-next v16
• Package manager: switched from npm to Bun (bun.lock replaces package-lock.json)

Want the original tutorial code? Check out commit 274eff7 (the last version before the refresh) or browse any earlier commit on this branch.

Before you begin, ensure you have:

• OpenRouter API key (or you can use grok or any other LLM providers)
• Exa search API key

git clone [repo-url]
cd Deep-Research-AI-Agent

This project uses Bun as the package manager.

bun install

Create a .env.local file in the root directory. Check .env.example for required variables.

bun run dev

Visit http://localhost:3000 to see your app.

Give a ⭐️ if this project helped you!

If you have any question or want a custom build for your business, you can reach out to me via:

• E-mail : codebucks27@gmail.com
• Twitter: https://twitter.com/code_bucks
• Instagram: https://www.instagram.com/code.bucks/

MyChannel: https://www.youtube.com/codebucks My Website: https://devdreaming.com/