AI Research Agent

A Python-based multi-step AI research agent built with LangChain, LangGraph, Firecrawl, and OpenAI. Performs structured web research with consistent, predictable results.

Features

• Structured Web Research - Searches and analyzes relevant articles
• Tool Extraction - Identifies relevant tools from web content
• Company Analysis - Scrapes official sites for pricing, tech stack, APIs
• Structured Output - Uses Pydantic schemas for consistent results
• Deterministic Workflow - LangGraph state nodes for reliable execution

Tech Stack

• Python 3.11+
• LangChain & LangGraph
• Firecrawl
• OpenAI API
• Pydantic

Setup

1. Clone and install

git clone https://github.com/yourusername/ai-research-agent.git
cd ai-research-agent
pip install -r requirements.txt

2. Configure environment

# Create .env file
OPENAI_API_KEY=your_openai_key
FIRECRAWL_API_KEY=your_firecrawl_key

3. Run

python main.py

How It Works

The pipeline has three main nodes:

1. Extract Tools – Search articles, scrape content, extract tool names
2. Research – Visit official sites, scrape data, analyze with schemas
3. Analyze – Aggregate data and produce recommendations

Example

$ python main.py
Enter your query: Google Cloud alternatives
# ... processing ...
# Structured output with tool analysis and recommendations

License

MIT