A specialized AI research agent designed to analyze and compare developer tools, technologies, and programming platforms. Built with LangGraph workflows and powered by Google's Gemini AI, this agent provides comprehensive analysis of tech stacks, pricing models, and developer experience insights.
- Intelligent Tool Discovery: Automatically extracts relevant developer tools from articles and search results
- Comprehensive Analysis: Analyzes pricing models, tech stacks, language support, and API availability
- Developer-Focused Research: Specializes in programming tools, frameworks, libraries, and platforms
- Structured Output: Returns organized data with clear recommendations
- Multi-Source Research: Combines search results with detailed web scraping for accurate information
- LangGraph: Workflow orchestration and state management
- Google Gemini 2.0: AI model for analysis and structured output
- Firecrawl: Web scraping and search capabilities
- Pydantic: Data validation and modeling
- Python: Core implementation language
- Python 3.8+
- Firecrawl API key
- Google Gemini API key
- Clone the repository:
git clone <repository-url>
cd deepresearch-agent- Install dependencies:
pip install -r requirements.txt- Set up environment variables:
Create a
.envfile in the root directory:
FIRECRAWL_API_KEY=your_firecrawl_api_key_here
GOOGLE_API_KEY=your_google_gemini_api_key_here- Install required packages:
pip install firecrawl-py langgraph langchain-google-genai python-dotenv pydanticRun the interactive CLI:
python main.pyThe agent works best with developer-focused queries:
"Python web frameworks""No-code database solutions""JavaScript testing libraries""Cloud hosting platforms""API documentation tools""React state management libraries"
📊 Results for: Python web frameworks
1. 🏢 FastAPI
🌐 Website: https://fastapi.tiangolo.com
💰 Pricing: Free
📖 Open Source: True
🛠️ Tech Stack: Python, Starlette, Pydantic, OpenAPI, JSON Schema
💻 Language Support: Python
🔌 API: ✅ Available
🔗 Integrations: SQLAlchemy, PostgreSQL, MongoDB, Redis
📝 Description: Modern, fast web framework for building APIs with Python
2. 🏢 Django
🌐 Website: https://www.djangoproject.com
💰 Pricing: Free
📖 Open Source: True
🛠️ Tech Stack: Python, SQLite, PostgreSQL, MySQL, Redis
💻 Language Support: Python
🔌 API: ✅ Available
🔗 Integrations: PostgreSQL, Redis, Celery, Docker
📝 Description: High-level Python web framework for rapid development
Developer Recommendations:
FastAPI is the best choice for modern API development due to its automatic OpenAPI documentation and excellent performance. Both are free and open-source. FastAPI offers superior developer experience with built-in validation and modern Python features.
- Tool Extraction: Searches for articles about the query topic and extracts specific tool names
- Research: Investigates each discovered tool by scraping official websites
- Analysis: Uses structured AI analysis to extract developer-relevant information
- Recommendations: Generates concise recommendations based on findings
Workflow: Main orchestrator using LangGraph state managementFirecrawlService: Handles web searching and scraping operationsCompanyInfo: Data model for tool/company informationCompanyAnalysis: Structured analysis output from AIDeveloperToolsPrompts: Specialized prompts for developer tool analysis
class CompanyInfo(BaseModel):
name: str
description: str
website: str
pricing_model: Optional[str] # Free, Freemium, Paid, Enterprise
is_open_source: Optional[bool]
tech_stack: List[str]
api_available: Optional[bool]
language_support: List[str]
integration_capabilities: List[str]
developer_experience_rating: Optional[str]- Pricing Models: Free, Freemium, Paid, Enterprise pricing structures
- Open Source Status: Whether tools are open source or proprietary
- Technology Stack: Programming languages, frameworks, databases supported
- API Availability: REST APIs, GraphQL, SDKs, programmatic access
- Language Support: Specific programming languages supported
- Integrations: Compatible tools, platforms, and services
FIRECRAWL_API_KEY: Your Firecrawl API key for web scrapingGOOGLE_API_KEY: Your Google Gemini API key for AI analysis
- Search Results Limit: Modify
num_resultsin search functions - Content Analysis Depth: Adjust content truncation limits
- Tool Extraction Count: Change the number of tools analyzed per query
- AI Model: Switch between different Gemini models in workflow.py
# Search for companies/tools
results = firecrawl.search_companies(query, num_results=5)
# Scrape specific URLs
content = firecrawl.scrape_company_pages(url)# Run complete research workflow
workflow = Workflow()
result = workflow.run("your developer tools query")- Requires active internet connection for web scraping
- API rate limits may apply depending on your Firecrawl/Gemini usage
- Analysis quality depends on the availability and quality of web content
- Some websites may block scraping attempts
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit your changes:
git commit -m 'Add amazing feature' - Push to the branch:
git push origin feature/amazing-feature - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
For issues, questions, or contributions:
- Open an issue on GitHub
- Check existing documentation
- Review the code comments for implementation details
- Caching System: Implement Redis caching for repeated queries
- Export Functionality: Add CSV/JSON export for research results
- Comparison Matrix: Visual comparison tables for multiple tools
- Historical Analysis: Track pricing and feature changes over time
- Integration Scoring: Quantitative scoring for developer experience
- Custom Filters: Filter results by pricing, language, or features