web-research-hub

Paul-Orlando/web-research-hub

★ 0 stars TypeScript AI/LLM Updated today

A full-stack AI research agent — three-agent pipeline (plan, search, synthesize) with live source tracking, search depth control, and document export. Originally prototyped in n8n + Replit, rebuilt as a standalone Next.js + FastAPI app with an MCP server tool layer.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "web-research-hub": {
      "command": "npx",
      "args": [
        "-y",
        "Paul-Orlando/web-research-hub"
      ]
    }
  }
}

README Excerpt

A hierarchical, three-agent web research pipeline that decomposes a research question into parallel search subtasks, executes them against live web sources via Exa, and synthesizes the results into a categorized, cited report — with a live source panel, real-time progress tracking, and export to PDF, DOCX, and Markdown.

Tools (9)

CORS_ORIGIN_REGEXDELETEEXA_API_KEYGETMCP_API_KEYMCP_SERVER_URLNEXT_PUBLIC_API_URLOPENROUTER_API_KEYPOST

Topics

exa-searchfastapigeminihierarchical-agentsmcpmulti-agentn8nopenrouterreplitresearch-automationwebhook

web-research-hub

Quick Install

README Excerpt

Tools (9)

Topics

Related AI/LLM Servers