FollowAgents AI AGENTS DIRECTORY
Home / All Agents / DB-GPT: Open-Source Agentic AI Data Assistant
Data & Analysis sql-generationdata-analysistext2sqlragawelreportingsandboxing

DB-GPT: Open-Source Agentic AI Data Assistant

Connect your data, let AI write SQL and code autonomously, execute in sandboxes, and turn analysis into reports, insights, and action.

View on GitHub ↗ Quick start ↓
Source repo
eosphoros-ai/DB-GPT
Stars
★ 20k
Last updated
8d ago
License
MIT
Primary language
Python
FA score
54/100 · Major gaps

At a glance

How it runs
CLISelf-hosted serviceWeb app
Works with
Universal · cross-platform
Cost
Free software; you pay for model usage
Setup effort
Low · running in minutes
You'll need
Python 3.10+uvDocker (optional)Shell / CLINetwork accessLocal filesystem
Typical use
Data analysts: upload a CSV file and get an AI-generated data overview with visual reports.
Not a fit if
  • Users unwilling to supply paid OpenAI, Moonshot, or MiniMax API keys
  • Enterprises needing mature commercial-grade docs and support
Source review
54/100 · Major gaps

What does this agent do, and when should you use it?

DB-GPT is an open-source agentic AI data assistant for the next generation of AI + Data products. It lets users and teams connect to databases, CSV/Excel files, warehouses, and knowledge bases, ask questions in natural language, and let AI autonomously write SQL and code. It runs Python- and code-driven analysis workflows, loads reusable skills for domain-specific tasks, and generates charts, dashboards, HTML reports, and analysis summaries. DB-GPT also serves as a platform for building AI-native data agents, workflows, and applications, with support for agents, AWEL, RAG, and multiple LLM providers. The project is MIT-licensed and offers one-line installation scripts and PyPI packages for quick deployment, with a web UI available at localhost:5670.

DB-GPT performs concrete operations: it reads from multiple data sources through connection managers (relational databases, CSV/Excel, documents, knowledge bases); uses an agent framework to plan tasks, break them into steps, call tools, and iterate; generates SQL from natural language and executes Python code for data cleaning, metric computation, and transformations; loads and runs reusable skills (e.g., SQL analysis skills, financial report analysis); executes code in sandboxed environments for safety; and produces outputs such as charts, dashboards, HTML reports, and summaries. Key components include the dbgpt CLI, FastAPI backend, agent execution engine, AWEL workflow engine, and RAG document parsing.

  1. Data analysts: upload a CSV file and get an AI-generated data overview with visual reports.
  2. Business users: ask questions about a database in plain English; AI writes the SQL and returns results.
  3. Finance teams: perform financial statement analysis with code, charts, and narrative summaries.
  4. Developers: use DB-GPT's framework to build custom AI data assistants with AWEL workflows.
  5. Enterprises: connect private data sources and knowledge bases, run analyses in a secure sandbox.

How do you install or deploy this agent?

Installation:

  1. One-line install (macOS/Linux):
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash

Or specify an API key:

curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | OPENAI_API_KEY=sk-xxx bash -s -- --profile openai
  1. PyPI install (requires Python 3.10+ and uv):
uv pip install dbgpt-app

Or with pip: pip install dbgpt-app.

  1. Docker installation: see official docs.

How do you use this agent?

After installation, start the server:

cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --profile <profile>

Or, with the PyPI package, simply run dbgpt start, then open http://localhost:5670. The first run launches an interactive wizard to choose an LLM provider and enter your API key. Then you can connect data sources, ask questions, run analyses, and generate reports through the Web UI.

What are this agent's strengths and limitations?

Pros
  • Supports a wide range of data sources (databases, CSV/Excel, knowledge bases) and multiple LLM providers (DeepSeek, Qwen, GLM, Llama, etc.), giving flexibility in model choice.
  • Provides sandboxed code execution for safer, more reliable analysis.
  • Built-in AWEL workflow and skill mechanisms allow building reusable domain-specific analysis pipelines.
  • One-line installer and PyPI package make deployment straightforward.
  • Generates visual reports, dashboards, and HTML outputs, supporting decision-making.
Limitations
  • Installation requires Python 3.10+ and uv, which may be a barrier for some environments.
  • Sandboxed execution may restrict certain operations requiring network or specific libraries.
  • Natural language to SQL accuracy depends on the chosen LLM; may need fine-tuning or careful model selection.
  • For large datasets or complex analyses, performance may be a concern.
  • Documentation and community support are less mature than commercial products; troubleshooting may require self-help.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
DB-GPT: Open-Source Agentic AI Data Assistant This agent 54 · Major gaps CLIFree + model costs ★ 20k 8d ago Python —
OpenChatBI — Conversational BI Agent 66 · Some gaps Library / SDKFree + model costs ★ 667 1d ago Python OpenAI API · Claude API
CAMEL Multi-Agent Framework 61 · Some gaps Library / SDKFree + model costs ★ 18k 7d ago Python OpenAI API
DATAGEN Research Assistant 44 · Major gaps CLIFree + model costs ★ 1.8k 17d ago Python OpenAI API · Claude API

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Major gaps
54/ 100 5-point scale 2.7 / 5
This review covers the source as of Aug 09, 2026. The project has shipped 1 stable release(s) since, which have not been re-reviewed. The score and verdict describe the reviewed version only. Recent releases ↓
Trust 10/29
Reliability 8/14
Adaptability 12/18
Convention 11/18
Effectiveness 9/13
Verifiability 4/8
Why each dimension lost points
Trust10 / 29 · 1.7/5

Evidence shows sandboxed execution, SQL steps exposing only executed SQL, parallel dispatch caps, and failure degradation, but no explicit least-privilege design, user confirmation, data flow transparency, sensitive data handling, dependency security audit, external effects control, rollback, or source attribution. Thus each criterion gets 1 for thin evidence.

Reliability8 / 14 · 2.9/5

Tests cover parallel dispatch, failure degradation, event forwarding, showing good internal consistency; dependency availability unverified, failure messages present in tests but not fully assessed. Self-consistency 2, dependency availability 1, failure messages 2.

Adaptability12 / 18 · 3.3/5

README shows multiple use cases (data analysis, SQL execution, multi-source access), capability boundaries described (e.g., parallel dispatch limits), trigger precision in tests, environment fit with Docker/source install. But boundaries and precision not fully covered, so 2 each.

Convention11 / 18 · 3.1/5

Clear information architecture (module split, docs links), detailed install notes, stable naming (version, package names), examples and FAQ provided, known limitations not explicitly listed, MIT license, changelog exists, maintenance responsibility via community and contributing guide. Known limitations 1, others 2.

Effectiveness9 / 13 · 3.5/5

Output usability verified by tests (summaries, event formats), high marginal value (multiple features), reasonable cost-benefit (open source free). But not quantified, so 2 each.

Verifiability4 / 8 · 2.5/5

Claims supported by tests and docs, but cross-source corroboration lacking (only repo-internal evidence), fact/inference separation good (tests distinguish). Claim traceability 2, cross-source 1, fact/inference 2.

Risks and how to mitigate them
  • No explicit least-privilege design; review default permission configurations.
  • User confirmation mechanism missing; add confirmation before sensitive actions.
  • Data flow transparency insufficient; clarify how data is collected, processed, and stored.
  • Dependency security not audited; check for known vulnerabilities.
  • Known limitations not listed; users may be unaware of boundaries.
Evidence confidence: Low Reviewed Aug 09, 2026 Reviewed revision c5fd00739969 New commits since this review; the score may not cover them
Review evidence README.hi.mdLICENSEpyproject.tomlworkflows/build-web.ymlworkflows/close-issue.ymltests/test_dispatch_prompt.pytests/test_dispatch_tool.py
See the full review method →

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v0.8.2
    Release notes excerpt
    ✨ Enhancements - support multi-file upload and analysis (#3206) - add OrcaRouter proxy provider (#3186) - add MaxCompute (ODPS) datasource support (#3105) (#3178) - Parallel sub-agent delegation execution (#3161) - Agentic Knowledge-Base Search (Indexing + Agentic RAG) (#3160) - add ask_question tool as builtin-tools (#3107) 🐞 Bug fixes - avoid KeyError when chart/sql run omits db\_name (#3199) - include flow uid in update\_flow PUT path (#3193) (#3196) - use LONGTEXT for large agent messages on MySQL (#3189) - move EXAMPLE\_1 database creation to end of schema file (#3183) …
    View on GitHub ↗
  2. v0.8.1
    Release notes excerpt
    ✨ Enhancements - Support Schedule task and MCP connector (#3095) - add CLIENT SETNAME to Valkey vector store client (#3090) - upgrade MiniMax default model to M3 (#3093) - Harden ~/.dbgpt/configs/\<profile>.toml file permissions to 0o600 (#3077) - adds context management, task-plan tracking, and the corresponding frontend UI. (#3053) - Implement VARBINARY and BINARY types for StarRocks (#3062) - add Valkey cache integration (#3057) - make distance metric configurable (#3044) - add Valkey vector store integration (#3051) - add LiteLLM as an embedded AI gateway provider (#3043) …
    View on GitHub ↗
  3. v0.8.0
    Release notes excerpt
    ✨ Enhancements - 🎉 DB-GPT V0.8.0 - Beta Testing (#2988) - Fix v0.7.5 documentation build failure with patch file (#2979) - add dbgpt app start cli (#2997) - upgrade MiniMax default model to M2.7 (#2993) - add MiniMax provider support (#2989) 🐞 Bug fixes - fix web api prcess url \& optmize doc image load performence (#3003) - add docsSidebar alias to versioned sidebars patches (#3002) - ignore leading vis-thinking block in react parser (#2996) 🛠️ Other improvements - update 0.8.0 version (#3004) - add v0.8.0 usage documentation (#2998) - update pacakge version (#2992) …
    View on GitHub ↗

FAQ

Which databases does DB-GPT support?
It supports common relational databases (e.g., MySQL, PostgreSQL) and other sources; see the official docs for the full list.
Can I use local models?
Yes, DB-GPT supports local deployment via vLLM, llama.cpp, etc., and offers many open-source models (LLaMA, Qwen, etc.).
Is code execution safe?
DB-GPT provides sandboxed execution environments to isolate code, but it's recommended to avoid running untrusted code.
What are the prerequisites for installation?
Python 3.10+ is required, and uv is recommended; the one-line installer works on macOS and Linux.
How can I extend with new data sources or skills?
You can add new data source connectors and write custom skills; refer to the official development guides.
View on GitHub ↗ Install ↓

Related agents

Data & Analysis

OpenChatBI — Conversational BI Agent

An open-source chat-based BI tool powered by LLMs that lets users query, analyze, and visualize warehouse data through natural language — no SQL required.
Data & Analysis

CAMEL Multi-Agent Framework

A Python framework for multi-agent collaboration, simulation, and synthetic-data generation.
Data & Analysis

DATAGEN Research Assistant

Automates hypothesis development, data analysis, visualization, and research report production.
Data & Analysis

OpenLens Research Agent

Turn a dataset and one research idea into an autonomous multimodal research workflow.