Deep Research Web UI

Active
GitHub TypeScript No License

Description

An AI-powered research assistant web UI that performs iterative, deep research on any topic by combining search engines with LLM reasoning.

Key Features

  • Client-side mode with API keys staying locally in the browser for maximum security
  • Real-time streaming AI responses with search visualization using tree structure
  • Multi-language web search support via Tavily, Firecrawl, and Google PSE providers
  • Export research reports as Markdown or PDF with citation support
  • Server Mode deployment with environment variables so users don't need API keys
  • Supports multiple AI providers including OpenAI-compatible, DeepSeek, Ollama, and OpenRouter

Use Cases

💡 Conducting iterative deep research on complex topics with AI-assisted search and analysis
💡 Producing structured research reports with citations for academic or business use
💡 Self-hosting a research assistant tool without exposing API keys to end users
💡 Exploring AI reasoning processes through the visual search flow tree diagram
💡 Rapid prototyping of research workflows with configurable AI and search providers

Tags

typescript agent llm web chatbot tools

Categories

💬 Chat UI ⚡ Agent Tools

Quick Start

1. Docker (server mode): docker run -p 3000:3000 -e NUXT_PUBLIC_SERVER_MODE=true -e NUXT_AI_API_KEY=your-key -e NUXT_PUBLIC_AI_PROVIDER=openai-compatible -e NUXT_WEB_SEARCH_API_KEY=your-search-key -e NUXT_PUBLIC_WEB_SEARCH_PROVIDER=tavily anotia/deep-research-web:latest
2. Or client mode: docker run -p 3000:3000 --name deep-research-web -d anotia/deep-research-web:latest
3. Open http://localhost:3000, configure API keys (client mode), and start researching
4. Live demo: https://deep-research.ataw.top
Visit GitHub

Related Projects