DeepAnalyze is an open source project that introduces an agentic large language model designed to perform autonomous data science tasks from start to finish. It is built to handle the entire data science pipeline, including data preparation, analysis, modeling, visualization, and report generation without requiring continuous human guidance. DeepAnalyze is capable of conducting open-ended data research across multiple data formats such as structured tables, semi-structured files, and unstructured text, enabling flexible and comprehensive analysis workflows. It integrates execution-based reasoning by generating and running code as part of its analysis process, allowing it to iteratively refine results and produce more accurate outputs. DeepAnalyze provides multiple interaction interfaces, including a web-based UI, a command-line interface, and a Jupyter-style notebook environment for interactive workflows.
Features
- Autonomous execution of full data science workflows from raw data to reports
- Supports structured, semi-structured, and unstructured data sources
- Built-in code generation and execution for iterative analysis tasks
- Multiple interfaces including CLI, Web UI, and Jupyter-based environment
- Open source model, dataset, and framework for extensibility and research
- Generates analyst-style reports with visualizations and insights