DATAGEN

Active
GitHub Python MIT

Description

DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.

Key Features

  • Multi-agent system with 8 specialized agents: hypothesis, process, visualization, code, searcher, report, quality review, and note taker
  • AI-driven hypothesis generation and validation with automated research direction optimization
  • Interactive data visualization and custom report generation with automated insight extraction
  • LangGraph-powered state graph managing the entire research workflow end-to-end
  • Progressive Disclosure architecture with skill-based configuration and dynamic tool loading
  • MCP integration for external server connectivity including filesystem, GitHub, and web search

Use Cases

💡 Automate end-to-end data analysis from hypothesis generation to final report writing
💡 Generate interactive data visualizations and dashboards from raw datasets
💡 Conduct AI-powered literature reviews and web research with multiple specialized agents
💡 Build custom research pipelines using configurable agent models and MCP tools
💡 Perform enterprise-grade data cleaning, transformation, and quality assurance

Tags

research-agent multi-agent langgraph python

Categories

🧠 Multi-Agent ⚡ Agent Tools

Quick Start

Clone the repo, create a conda environment with `conda create -n datagen python=3.10`, install dependencies with `pip install -r requirements.txt`, configure `.env` with your API keys, place a data file in the `data/` directory, then run `python main.py`.
Visit GitHub

Related Projects