How does Deep Research protect my privacy?
All data is processed and stored locally in your browser. When using the local API mode, no API keys or server-side configurations are needed.
@u14app
基本信息
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"deep-research": {
"command": "docker",
"args": [
"pull",
"xiangfa/deep-research:latest"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Deep Research is an open-source AI-powered tool that generates in-depth research reports in about two minutes. It supports multiple large language models and search engines, processes and stores all data locally in the browser to protect user privacy, and can be deployed on Vercel, Cloudflare, Docker, or as a static site.
Use the free Gemini model by obtaining a Gemini API key, then deploy the project with a one-click button to Vercel or Cloudflare, and start using. For other LLMs, set the LLM API key and optional API base URL after deployment. For local development, clone the repository, install dependencies with pnpm, set environment variables via env.tpl, and run pnpm dev.
All data is processed and stored locally in your browser. When using the local API mode, no API keys or server-side configurations are needed.
It supports Gemini, OpenAI, Anthropic, Deepseek, Atlas Cloud, Grok, Mistral, Azure OpenAI, OpenAI-compatible LLMs, OpenRouter, Ollama, etc. For search, it supports Searxng, Tavily, Firecrawl, fastCRW, Exa, Bocha, Brave, and others.
Yes, you can deploy it on Vercel, Cloudflare Pages, using Docker, or as a static export. Detailed guides are provided for each method.
Yes, it provides a Server-Sent Events (SSE) API and a Model Context Protocol (MCP) server. You can use the SSE API to start research tasks and receive real-time results.
Yes, Deep Research is MIT licensed and freely available for personal and commercial use.

Connect your AI to millions of laws and court cases! Lawstronaut is the infrastructure layer that connects AI agents and software to millions of legal documents across 150+ jurisdictions, structured legal data, continuou
Hosted TikTok MCP server for AI agents: read public profiles, account videos, comments and replies, or search videos and creators. Structured JSON for creator research and content analysis.
Read public Instagram profiles and post feeds by handle in Claude, Cursor, and other MCP clients. Get follower counts, captions, hashtags, mentions, and engagement counts as structured JSON.
Official MCP server for the Sugra API, giving AI agents source-attributed access to 1,500+ endpoints across 36 data domains from 160+ primary sources. Covers markets, economics, company fundamentals, government, news, cl

SportsTrackLive is a remote MCP server available at https://mcp.sportstracklive.com. SportsTrackLive is a Live Tracking solution and let you record, share and relive your Tracks! SportsTrackLive provide a real-time tra
评论