pepolehub  by MeirKaD

AI-powered platform for professional search and research

Created 3 months ago
318 stars

Top 85.2% on SourcePulse

GitHubView on GitHub
Project Summary

PeopleHub is an open-source AI platform tackling inefficient and costly manual LinkedIn searches and professional research. It targets professionals needing rapid access to talent and intelligence, offering natural language search, intelligent multi-tier caching for cost reduction, and automated AI-driven research reports.

How It Works

It employs Google Gemini 2.0 for natural language query parsing, Bright Data APIs (Google Search, LinkedIn Scraper) for data acquisition, and LangGraph for automated research workflows. A multi-tier caching system (Redis hot cache, PostgreSQL persistent cache) minimizes external API calls and costs. AI research reports automate due diligence via stateful, multi-step workflows, including web scraping and AI summarization.

Quick Start & Requirements

Install via git clone https://github.com/MeirKaD/pepolehub and npm install. Requires Node.js 18+, Supabase, Bright Data (API token), and Google AI (Gemini 2.0) API keys. Configure credentials in .env. Database setup uses Prisma (npx prisma db push). Run with npm run dev. Setup necessitates obtaining multiple third-party API credentials.

Highlighted Details

  • Natural Language Search: Plain English queries simplify professional discovery.
  • AI Research Reports: Automate due diligence with LangGraph, including profile analysis and summarized findings.
  • Multi-Tier Caching: Claims 70-90% cost reduction and sub-millisecond cache lookups, improving performance significantly.
  • UI: Features glassmorphism design with 3D animations.

Maintenance & Community

Contributions are welcomed via pull requests. Built by Meir Kadosh. No specific community channels or roadmap details are provided.

Licensing & Compatibility

Released under the MIT License, permissive for commercial use and integration.

Limitations & Caveats

Functionality heavily relies on paid third-party APIs (Bright Data, Google AI), posing operational costs and adoption barriers. Initial data retrieval can take up to 120 seconds due to scraping bottlenecks. Setup complexity involves managing multiple external service accounts and API keys.

Health Check
Last Commit

1 month ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
0
Star History
169 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.