eosphoros-ai/db-gpt

📈 Trending★ 18,784PythonAudience · pm founderComplexity · 3/5ActiveLicenseSetup · moderate

Mindmap

mindmap
  root((repo))
    What it does
      Natural language queries
      SQL generation
      Multi-step workflows
      Charts and reports
    Data sources
      Databases
      Spreadsheets
      CSV files
      Custom sources
    Key features
      Reusable skills
      Sandboxed execution
      Web interface
      Multiple AI models
    Use cases
      Business analysis
      Financial reports
      Database exploration
      Data profiling
    Tech stack
      Python
      AI agents
      SQL execution
      Web UI

mindmap root((repo)) What it does Natural language queries SQL generation Multi-step workflows Charts and reports Data sources Databases Spreadsheets CSV files Custom sources Key features Reusable skills Sandboxed execution Web interface Multiple AI models Use cases Business analysis Financial reports Database exploration Data profiling Tech stack Python AI agents SQL execution Web UI

Things people build with this

USE CASE 1

Ask questions about your company's database and get instant SQL queries and visualizations without writing code.

USE CASE 2

Build reusable analysis workflows (skills) for recurring business questions like monthly revenue reports or customer segmentation.

USE CASE 3

Explore and profile CSV files or spreadsheets by asking natural language questions instead of manually writing formulas.

USE CASE 4

Create dashboards and written reports from multi-step data analysis workflows that run automatically.

Tech stack

PythonSQLWeb UIAI modelsAgents

Getting it running

Difficulty · moderate Time to first run · 30min

Requires API key for AI models and database connection setup.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

In plain English

DB-GPT is an open-source AI assistant for working with data. Instead of writing database queries by hand, you can ask questions in plain English and the system figures out the SQL needed to answer them. It can connect to databases, spreadsheets, CSV files, and other data sources, then let an AI plan and execute multi-step analysis workflows automatically. The project is designed as an agentic system, meaning the AI can break a task into steps, write code or SQL at each step, run it in a sandboxed environment for safety, and compile the results into charts, dashboards, or written reports. Users can also create reusable "skills," which are packaged workflows for common analysis tasks that can be loaded and re-run whenever needed. DB-GPT supports multiple AI model providers and can be installed with a single command on macOS or Linux. Once running, it opens a web interface at a local address. The platform is aimed at individuals and teams who want to ask business questions of their data without needing a data analyst, from financial analysis to database profiling to CSV exploration. It is released under the MIT license and supports a wide range of AI backends.

Copy-paste prompts

Prompt 1

I have a CSV file with sales data. How do I load it into DB-GPT and ask it questions like 'What were my top 5 products by revenue last quarter?'

Prompt 2

Show me how to create a reusable skill in DB-GPT that calculates monthly churn rate from my customer database.

Prompt 3

I want to connect DB-GPT to my PostgreSQL database and generate a dashboard showing KPIs. What are the setup steps?

Prompt 4

How do I use DB-GPT to write and execute a multi-step analysis that joins three tables, filters by date, and outputs a chart?

Open on GitHub → Explain another repo

Generated 2026-05-18 · Model: sonnet-4-6 · Verify against the repo before relying on details.