An AI-powered data analysis platform that converts natural language queries into executable Python code and runs it securely. Fully compatible with Streamlit Cloud, using LangGraph for workflow orchestration, Google Gemini for code generation, and codibox for dual backend execution (Host/Docker).

🤖 AgenticDataAnalyst

An AI-powered data analysis platform that converts natural language queries into executable Python code and runs it securely.

Fully functional and Streamlit Cloud compatible! The system uses LangGraph for workflow orchestration, Google Gemini for code generation, and codibox for secure code execution with dual backend support (Host/Docker).

✨ Features

• 🧠 Natural Language to Code: Converts user queries into executable Python code using AI
• 🔍 Intelligent File Selection: Automatically selects relevant datasets using semantic search
• ⚡ Dual Backend Execution:
  • Host backend (default): Fast execution, works on Streamlit Cloud
  • Docker backend (optional): Secure, isolated execution for local development
• 📊 Visualization Generation: Automatically creates charts and visualizations
• 🔄 Error Recovery: Automatic code refinement with up to 3 retry attempts
• 🤖 AI-Powered Metadata: Generates dataset descriptions and summaries automatically
• 🌐 Multiple Interfaces: CLI, Streamlit web app, and programmatic API

📸 Demo

Main Interface

Analysis Results

Interactive web interface for natural language data analysis with AI-powered insights

Project Structure

AgenticDataAnalyst/
├── agent_coder/              # AI workflow system
│   ├── agents.py             # FileAccessAgent, CodeGenerationAgent, CodeExecutor
│   ├── workflow.py           # LangGraph workflow definitions
│   ├── simple_workfl