Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt

Use this file to discover all available pages before exploring further.

1. Introduction

Deep Research Web UI is an AI-powered research assistant that combines search engines, web scraping, and LLMs to autonomously research a topic and produce a comprehensive report. Key features:
  • Low cost — Achieve “deep research” capabilities similar to ChatGPT, Perplexity, and other products at a fraction of the cost
  • Privacy-first — All configurations and API requests run in the browser, with self-hosting support
  • Real-time feedback — Stream AI responses and display them live in the UI
  • Search visualization — Tree-structured visualization of the research process
  • PDF export — Export final reports as Markdown and PDF
  • Multi-model support — Compatible with many LLM providers
GitHub Repository

2. Setup

Open the Deep Research Web UI, click the ⚙️ button in the top-right corner to open settings.

2.1 Configure Anyfast as the AI provider

  • Sign up or log in at the Anyfast console.
  • Go to API Keys, generate a new API Key, and copy it.
  • In the Deep Research settings, under AI Service, select OpenAI Compatible.
  • Set the Base URL to https://www.anyfast.ai/v1.
  • Paste your Anyfast API Key.
  • Select your preferred model (e.g., gpt-4o, claude-opus-4-7).
  • (Optional) Set the Context Length for large-scale research.

2.2 Configure a search service

Tavily is recommended — it offers 1,000 free searches per month:
  • Sign up at Tavily and create an API Key.
  • In the Deep Research settings, under Search Service, select Tavily and paste your Tavily API Key.
  • (Optional) Set the search language.

3. Start researching

You’re all set! Enter a research topic and let the AI dive deep. The research tree will show progress in real time, and you can export the final report as Markdown or PDF.