---
title: "Deploy Deep Research Web UI"
description: "AI deep-research agent that writes cited reports from live web search"
category: "AI/ML"
url: https://railway.com/deploy/deep-research-web-ui
---

# Deploy Deep Research Web UI

AI deep-research agent that writes cited reports from live web search

**[Deploy Deep Research Web UI on Railway](https://railway.com/template/deep-research-web-ui)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/deep-research-web-ui/manifest.json

- **Creator:** My Projects
- **Category:** AI/ML

## Template content

### Deep Research Web https://raw.githubusercontent.com/AnotiaWang/deep-research-web-ui/main/public/favicon.ico

- **Image:** anotia/deep-research-web:latest
- **Health check:** /
- **Public domain:** Yes

## Documentation

# Deploy and Host Deep Research Web UI on Railway

[Deep Research Web UI](https://github.com/AnotiaWang/deep-research-web-ui) is an open-source AI deep-research agent that turns any question into a **cited report**: it plans searches, browses the web, verifies findings against real source pages, visualizes the research tree, and lets you inspect and follow up on every citation. Export reports to Markdown or PDF.

## About Hosting Deep Research Web UI

This template runs the official `anotia/deep-research-web` image (Nuxt/Nitro server) as a single stateless service with a public HTTPS domain and healthcheck. No database is required — research history is stored in each visitor's browser.

By default the app runs in **Client Mode**: every visitor enters their own AI and web-search API keys in the browser settings, so the public instance never exposes your keys. Supported providers include OpenAI, OpenAI-compatible endpoints (OpenRouter, DeepSeek, Ollama, LM Studio…), Gemini, Anthropic and more, with Tavily, Firecrawl, Google PSE or SearXNG for web search.

## Common Use Cases

- Market, competitor and technology research with verifiable citations
- Fact-checking: inspect source excerpts and run targeted follow-ups that update only affected passages
- A private "Perplexity-style" research tool for your team using your own model provider
- Multilingual research (search and report languages are configurable)

## Dependencies for Deep Research Web UI Hosting

- Docker image `anotia/deep-research-web`
- An LLM API key and a web-search API key (entered in the browser in Client Mode)

### Deployment Dependencies

- Source: https://github.com/AnotiaWang/deep-research-web-ui
- Configuration reference: https://github.com/AnotiaWang/deep-research-web-ui#readme

### Implementation Details

**Optional Server Mode** (shared keys configured on the server, no key entry for users) — add these variables to the service:

```
NUXT_PUBLIC_SERVER_MODE=true
NUXT_AI_API_KEY=your-ai-api-key
NUXT_WEB_SEARCH_API_KEY=your-search-api-key
NUXT_PUBLIC_AI_PROVIDER=openai-compatible
NUXT_PUBLIC_AI_MODEL=gpt-4o-mini
NUXT_PUBLIC_WEB_SEARCH_PROVIDER=tavily
```

⚠️ Server Mode lets anyone who can reach the URL spend your API credits — only enable it behind access control (e.g. a private domain or an auth proxy).

## Why Deploy Deep Research Web UI on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Deep Research Web UI on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/deep-research-web-ui