DB-GPT

Active
GitHub Python MIT

Description

DB-GPT is an open-source agentic AI data assistant framework integrating multi-agent collaboration, RAG, and AWEL workflow engine, purpose-built for AI+Data applications.

Key Features

  • Agentic data analysis with end-to-end task planning, tool calling, and workflow execution
  • Autonomous SQL and Python code generation for data querying and analysis
  • Multi-source data access: databases, CSV/Excel, data warehouses, and knowledge bases
  • Skills-driven extensibility for packaging domain knowledge into reusable workflows
  • Sandboxed execution environments for safe and reliable code running
  • Generates charts, dashboards, HTML reports, and analysis summaries

Use Cases

πŸ’‘ Analyze CSV/Excel files and generate visual reports
πŸ’‘ Connect to databases and produce profiling reports with natural language queries
πŸ’‘ Perform financial report analysis with code, charts, and narrative summaries
πŸ’‘ Build AI-native data assistants for teams and products
πŸ’‘ Create and reuse SQL analysis skills and domain workflows

Tags

database multi-agent rag python

Categories

🧠 Multi-Agent πŸ“š RAG Tools

Quick Start

1. Install: curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash
2. Or with API key: curl ... | OPENAI_API_KEY=sk-xxx bash -s -- --profile openai
3. Start: cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --profile <profile>
4. Open http://localhost:5670
Visit GitHub Visit Website

Related Projects