Realtor Research Agent

An AI-powered research agent built with the Claude Agent SDK that gathers comprehensive information about US and Canadian realtors using only their email address.

Overview

This agent leverages multiple search APIs (Perplexity, Exa) to discover, verify, and compile professional information about real estate agents, including:

• License verification
• Brokerage affiliation
• Professional background
• Contact information
• Market specialization
• Social media presence

Prerequisites

• Node.js 18.0.0 or higher
• API keys for:
  • Anthropic Claude API
  • Perplexity API
  • Exa API

Installation

# Clone the repository
git clone https://github.com/mbnocode/researchagent.git
cd researchagent

# Install dependencies
npm install

# Configure environment variables
cp .env.example .env
# Edit .env and add your API keys

Configuration

Edit .env file with your API keys:

ANTHROPIC_API_KEY=your_key_here
PERPLEXITY_API_KEY=your_key_here
EXA_API_KEY=your_key_here

Usage

# Development mode
npm run dev

# Build for production
npm run build

# Run production build
npm start

Project Structure

researchagent/
├── src/
│   ├── agent/           # Core agent logic
│   ├── tools/           # Search tool integrations
│   ├── workflows/       # Research workflows
│   ├── types/           # TypeScript type definitions
│   ├── utils/           # Utility functions
│   └── index.ts         # Entry point
├── tests/               # Test files
└── dist/                # Compiled output

How It Works

1. Email Analysis: Extracts realtor name and brokerage hints from email address
2. Multi-Source Search: Queries Perplexity and Exa APIs in parallel
3. Data Aggregation: Combines and verifies information from multiple sources
4. Report Generation: Creates structured profile with confidence scores

Development

# Run linter
npm run lint

# Run tests
npm test

# Watch mode for development
npm run dev

License

MIT