MaliSafi is a web application that uses AI agents to find, analyze, and report on property.
- AI-powered property search across multiple real estate websites
- Comparative market analysis of property investment opportunities
- Location-based price trend analysis
- Comprehensive property reports with recommendations
- Backend: Flask, Python
- Frontend: HTML, CSS, JavaScript
- AI: CrewAI multi-agent framework, LangChain
- Data: Web scraping from major Kenyan real estate websites
-
Clone the repository:
git clone https://github.com/fourbic/malisafi.git cd malisafi -
Create and activate a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Create a
.envfile with your API keys:OPENAI_API_KEY=your_openai_api_key FIRECRAWL_API_KEY=your_firecrawl_api_key FLASK_APP=app.py FLASK_ENV=development
-
Test it out on the notebook and for a webapp the project uses a Flask application: Notebook can be found here
/notebook/realEstate_MultiAgent_Crew.ipynb -
Flask runs on your browser and navigate to:
http://localhost:5000 -
Enter your property search criteria or select from the popular search cards on the homepage.
-
Wait for the AI agents to analyze properties and generate a report.
MaliSafi/
├── ai_agents/ # AI agent modules
│ ├── __init__.py
│ └── real_estate_agents.py
├── static/ # Static assets
│ ├── css/
│ │ └── style.css
│ ├── js/
│ │ └── main.js
│ └── img/
│ └── logo.svg
├── templates/ # HTML templates
│ ├── index.html
│ ├── results.html
│ └── about.html
├── app.py # Main Flask application
├── .env # Environment variables (not in version control)
├── requirements.txt # Project dependencies
└── README.md # This file
This project is licensed under the MIT License - see the LICENSE file for details.
This project uses the CrewAI framework for multi-agent orchestration.