Quick Install
The fastest way to get DB-GPT running. The installer script prepares a local DB-GPT workspace, generates a provider profile, and gives you a ready-to-run webserver command.
Recommended: installer scriptâ
Use the installer script if you want the shortest path from zero to a working DB-GPT web UI.
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bashSystem requirementsâ
This quick-install flow is designed for:
- macOS or Linux
- a shell environment that can run
bash - network access to download dependencies
- an API key if you plan to use a hosted model provider immediately
Choose this path if you want to try DB-GPT quickly without managing the repository structure yourself.
Install with a provider profileâ
If you already know which provider you want, pass the profile and API key directly during installation.
OpenAI-compatible profileâ
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | OPENAI_API_KEY=sk-xxx bash -s -- --profile openaiKimi 2.5 via Moonshot APIâ
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | MOONSHOT_API_KEY=sk-xxx bash -s -- --profile kimiMiniMax via an OpenAI-compatible APIâ
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | MINIMAX_API_KEY=sk-xxx bash -s -- --profile minimaxReuse an existing local checkoutâ
Already have a local DB-GPT repository? Reuse it instead of cloning into ~/.dbgpt/DB-GPT.
Reuse local repo with OpenAIâ
OPENAI_API_KEY=sk-xxx bash scripts/install/install.sh --profile openai --repo-dir "$(pwd)" --yesReuse local repo with Kimiâ
MOONSHOT_API_KEY=sk-xxx bash scripts/install/install.sh --profile kimi --repo-dir "$(pwd)" --yesReuse local repo with MiniMaxâ
MINIMAX_API_KEY=sk-xxx bash scripts/install/install.sh --profile minimax --repo-dir "$(pwd)" --yesWhat the installer preparesâ
The installer script sets up the common runtime layout for you:
- a DB-GPT checkout under
~/.dbgpt/DB-GPTunless--repo-diris used - generated provider configs under
~/.dbgpt/configs/ - the DB-GPT home directory under
~/.dbgpt/ - a ready-to-run webserver command using the generated profile
Start DB-GPT after installationâ
After installation completes, start the webserver with the generated profile config:
cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --profile <profile>Then open http://localhost:5670.
Verify the installâ
Your install is working if:
- the webserver starts without configuration errors
- the Web UI opens at
http://localhost:5670 - you can start a chat in the browser
Review the script firstâ
If you prefer to inspect the installer before running it:
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh -o install.sh
less install.sh
bash install.sh --profile openai
Alternative install methodsâ
If the installer script is not the right fit for your environment:
- use CLI Install for a PyPI-based install with the
dbgptcommand - use Source Install for development, debugging, and customization
Troubleshootingâ
The installer script does not match my shell or platformâ
Use CLI Install or Source Install instead.
I want more control over dependencies and configurationâ
Use Source Install. It exposes the full repository layout and uv sync workflow.
The install completed, but DB-GPT does not start cleanlyâ
Check the generated config under ~/.dbgpt/configs/, then see Installation Issues.