Verified project record

eosphoros-ai/DB-GPT

An open-source agentic AI data assistant that connects to diverse data sources and performs text-to-SQL, code execution, and report generation. It requires an LLM provider (API or local) and supports private deployment with sandboxed execution environments.

Project overview

Project type: AI Agent · RAG · Data Processing
Use cases: Knowledge Q&A · Data Analysis
Deployment: Refer to project documentation
License: MIT

Best for

Developers and data teams who need to build or run agentic workflows for text-to-SQL, code execution, and data analysis across multiple data sources.

Key capabilities

Plans tasks, breaks work into steps, calls tools, and completes analysis workflows end to end.
Generates SQL and code to query data, clean datasets, compute metrics, and produce outputs.
Works across structured and unstructured sources, including databases, spreadsheets, documents, and knowledge bases.
Packages domain knowledge, analysis methods, and execution workflows into reusable skills.
Runs code and tools in isolated environments for safer, more reliable analysis.
Produces charts, dashboards, HTML reports, and decision-ready outputs.

Limitations and risks

Core functionality requires a configured LLM provider, either through external paid services or locally hosted models.
Telemetry practices are currently not documented.

Getting started

Run the one-line curl installer script or use the PyPI package (pip install dbgpt-app). The setup includes an interactive wizard to configure the environment.

Evidence and sources

GitHub project description: open-source agentic AI data assistant for the next generation of AI + Data products.
README: DB-GPT is an open-source **agentic AI data assistant** for the next generation of **AI + Data** products. It helps users and teams: - connect to **databases, CSV / Excel files, wa…
README: db-gpt
README: Plan tasks, break work into steps, call tools, and complete analysis workflows end to end.
README: Generate SQL and code to query data, clean datasets, compute metrics, and produce outputs.

Reviewed at: 2026-07-17T12:01:02Z