# DB-GPT

open-source agentic AI data assistant for the next generation of AI + Data products.

Repository: https://github.com/eosphoros-ai/DB-GPT
Canonical: https://ross.abutalabs.com/products/db-gpt
Homepage: http://docs.dbgpt.cn
Language: Python
License: MIT
License Family: permissive
Topics: database, gpt-4, vicuna, private, security, llm, agents, bgi, gpt, rag, hacktoberfest, deepseek
Last push: 2026-08-26T11:10:31+00:00
Link (homepage): http://docs.dbgpt.cn
Link (site_page): http://docs.dbgpt.cn/docs/overview
Link (site_page): http://docs.dbgpt.cn/docs/next/overview
Link (site_page): http://docs.dbgpt.cn/docs/v0.8.0/overview
Link (site_page): http://docs.dbgpt.cn/docs/installation

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 87, longevity 88
- inputs: {"age_days": 1238, "days_push": 7, "days_rel": 7, "gap_med": 43.5, "n_releases_24m": 13}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 19800, forks 2892 (observed 2026-08-28T04:11:29.241988+00:00)

## What it is
DB-GPT is an open-source agentic AI data assistant that connects to databases, spreadsheets, and knowledge bases, autonomously writes SQL and code, and turns analysis into charts, dashboards, and reports. It also serves as a platform for building AI-native data agents and workflows using its AWEL orchestration language, RAG, and multi-model management framework.

## Use cases
- query databases with natural language
- convert business questions to SQL automatically
- analyze CSV and Excel files with AI
- generate charts and analysis reports from data
- build AI agents for data tasks
- run RAG over internal knowledge bases
- chat with my database privately
- orchestrate LLM workflows for data analysis

## When to choose
- you want a self-hosted, private AI assistant over your databases and files
- you need natural-language-to-SQL plus autonomous code execution in one tool
- you want to build agentic data workflows with RAG and multiple LLM providers
- you need sandboxed execution and report generation for data analysis

## When to avoid
- you only need a lightweight text-to-SQL library to embed in an existing app
- you cannot run a web server or lack GPU/API access for LLMs
- you need a fully managed cloud data platform with enterprise support
- your use case is general chatbot building unrelated to data

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, llm-inference, chatbot, data-visualization, database, workflow-automation, web-framework
- domain: artificial-intelligence, databases, data-science, large-language-models, analytics, developer-tools
- platform: python, self-hosted
- tags: text-to-sql, awel, multi-model-management, sandboxed-code-execution, data-assistant, chat-with-data, mit-license, ai-agents, retrieval-augmented-generation, linux, macos, docker, web-server, gpu

## Member repositories
- eosphoros-ai/DB-GPT (main) score 93
- eosphoros-ai/DB-GPT-Hub (plugin) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:29.241988+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:59:32.810551+00:00, confidence not recorded.
  - readme: https://github.com/eosphoros-ai/DB-GPT (fetched 2026-08-28T04:11:29.241988+00:00, sha e9856efbb23e)
  - homepage: http://docs.dbgpt.cn (fetched 2026-08-29T07:58:15.565525+00:00, sha 1065d909c200)
  - site_page: http://docs.dbgpt.cn/docs/overview (fetched 2026-08-29T07:58:15.574850+00:00, sha e3815b3c8254)
  - site_page: http://docs.dbgpt.cn/docs/next/overview (fetched 2026-08-29T07:58:15.577339+00:00, sha ed03e3cf3471)
  - site_page: http://docs.dbgpt.cn/docs/v0.8.0/overview (fetched 2026-08-29T07:58:15.579380+00:00, sha 7c3f81c25200)
  - site_page: http://docs.dbgpt.cn/docs/installation (fetched 2026-08-29T07:58:15.581175+00:00, sha 683f6adac1ce)
  - site_page: http://docs.dbgpt.cn/docs/use_cases (fetched 2026-08-29T07:58:15.582740+00:00, sha dc3a4c2b3c23)
  - site_page: http://docs.dbgpt.cn/docs/getting-started/deploy/source-code (fetched 2026-08-29T07:58:15.584366+00:00, sha 085ead6979dd)
  - site_page: http://docs.dbgpt.cn/docs/getting-started/cli-quickstart (fetched 2026-08-29T07:58:15.586616+00:00, sha 246b1bd77f08)
  - site_page: http://docs.dbgpt.cn/docs/installation/docker (fetched 2026-08-29T07:58:15.589894+00:00, sha c1df8716be22)
- Data as of 2026-08-30T08:39:29.467469+00:00.