DB-GPT

What is DB-GPT?

DB-GPT is an open-source agentic data assistant. It connects to databases and files, answers questions by writing and running SQL or Python, builds knowledge bases (RAG) from documents, and turns analysis into reports and dashboards. Agents and workflows (AWEL) can be built on top, and it works with cloud model APIs such as OpenAI, DeepSeek, Qwen or SiliconFlow as well as local models through vLLM or llama.cpp. The default Docker Compose stack runs the web server with MySQL for metadata.

Where it fits in a 10–200 person business

• Let staff ask questions of a sales or ERP database in plain language and get the SQL and a chart back
• Generate recurring analysis reports from spreadsheets and databases
• Build a document knowledge base that sits next to your business data

These use cases are our editorial suggestions, not claims made by the project.

Can a business use DB-GPT? (license)

This is a plain-English summary of the license text, not legal advice. Third-party models you run with it have their own licenses.

Data & compliance: does DB-GPT phone home?

Checked against the project's own docs and repository on Nov 3, 2026. "Not documented" means we could not find the answer in official sources; it does not mean the feature is missing or that no data is sent. Third-party services you connect (model APIs, vector databases, search engines) have their own data policies. Compare all apps.

What hardware does DB-GPT need?

The "System resources" table lists 2 cores / 4 GB RAM / 10 GB disk for "API proxy only", 4 cores / 16 GB / 30 GB for a local 7B model and 8 cores / 32 GB / 60 GB for local 13B+ models. Docker 20.10+ and Docker Compose 2.0+ are required for the Docker route.

Source: github.com/eosphoros-ai/DB-GPT/blob/main/docs/docs/getting-started/prerequisites.md

How much does it cost to host DB-GPT per month?

How to deploy DB-GPT

Method: Docker Compose (web server + MySQL)

git clone https://github.com/eosphoros-ai/DB-GPT.git && cd DB-GPT
export SILICONFLOW_API_KEY="your-siliconflow-api-key"
SILICONFLOW_API_KEY=${SILICONFLOW_API_KEY} docker compose up -d
# open http://localhost:5670

From the official instructions: github.com/eosphoros-ai/DB-GPT/blob/main/docs/docs/getting-started/deploy/docker-compose.md. Always check the source for the current version before you run it.

Known gotchas when self-hosting DB-GPT

• The default docker-compose.yml sets the MySQL root password to "aa123456" and publishes MySQL on port 3306. Change the password and drop the port mapping before running it on a reachable server. source
• "docker compose down -v" removes all volumes, including the MySQL database; all data is lost. source
• The Compose file uses the eosphorosai/dbgpt-openai:latest image and SiliconFlow as the default model provider. Pin an image tag and switch the TOML config if you use another provider. source
• On first start the web server waits for MySQL to initialise and may fail and auto-restart; check docker logs db-gpt-webserver-1. source

Alternatives in AI app & agent builders

• AutoGPT Platform Visual builder for long-running AI agents and workflows, self-hostable as a single container. Compare AutoGPT Platform vs DB-GPT
• Dify Visual platform for building LLM apps, RAG chatbots, agents and workflows. Compare DB-GPT vs Dify
• Langflow Visual builder for AI agents and RAG flows that you can deploy as APIs or MCP servers. Compare DB-GPT vs Langflow
• Mem0 Long-term memory layer for AI assistants and agents, with a self-hosted REST server and dashboard. Compare DB-GPT vs Mem0
• Flowise Drag-and-drop builder for LLM agents and chatflows (archived August 2026).
• CowAgent Self-hosted AI agent (formerly chatgpt-on-wechat) that answers in WeChat, WeCom, Feishu, DingTalk, Slack and a web console. Compare CowAgent vs DB-GPT
• AstrBot Multi-platform AI chatbot and agent framework for QQ, WeCom, Feishu, DingTalk, Official Accounts, Telegram and Slack. Compare AstrBot vs DB-GPT
• Sim Visual builder for AI agent workflows, with knowledge bases, integrations and an API. Compare DB-GPT vs Sim
• Coze Studio Open-source edition of ByteDance's Coze agent-building platform. Compare Coze Studio vs DB-GPT
• Agent Zero General-purpose personal AI agent that uses its own Linux environment, browser, memory and tools. Compare Agent Zero vs DB-GPT

Sources

• GitHub repository: github.com/eosphoros-ai/DB-GPT
• Official documentation, Deploy instructions, Gotcha 2, Gotcha 3, Gotcha 4: github.com/eosphoros-ai/DB-GPT/blob/main/docs/docs/getting-started/deploy/docker-compose.md
• License text: github.com/eosphoros-ai/DB-GPT/blob/main/LICENSE
• Hardware requirements: github.com/eosphoros-ai/DB-GPT/blob/main/docs/docs/getting-started/prerequisites.md
• Gotcha 1: github.com/eosphoros-ai/DB-GPT/blob/main/docker-compose.yml
• Hetzner Cloud pricing (cost estimate): www.hetzner.com/cloud/regular-performance
• GitHub stars, commits and releases: GitHub REST API, fetched Nov 3, 2026