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).
# š¤ AgenticDataAnalyst > An AI-powered data analysis platform that converts natural language queries into executable Python code and runs it securely. [](https://www.python.org/) [](https://streamlit.io/) [](LICENSE) [](https://github.com) **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 - š§ **Natural Language to Code**: Converts user queries into executable Python code using AI - š **Intelligent File Selection**: Automatically selects relevant datasets using semantic search - ā” **Dual Backend Execution**: - **Host backend** (default): Fast execution, works on Streamlit Cloud - **Docker backend** (optional): Secure, isolated execution for local development - š **Visualization Generation**: Automatically creates charts and visualizations - š **Error Recovery**: Automatic code refinement with up to 3 retry attempts - š¤ **AI-Powered Metadata**: Generates dataset descriptions and summaries automatically - š **Multiple Interfaces**: CLI, Streamlit web app, and programmatic API ## šø Demo ### Main Interface  ### Analysis Results  *Interactive web interface for natural language data analysis with AI-powered insights* ## Project Structure ``` AgenticDataAnalyst/ āāā agent_coder/ # AI workflow system ā āāā agents.py # FileAccessAgent, CodeGenerationAgent, CodeExecutor ā āāā workflow.py # LangGraph workflow definitions ā āāā simple_workfl
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.