Giskard provides open source evaluation and testing tools for LLM agents.
DB GPT
DB-GPT is an open-source agentic data assistant for AI and data products.

About DB GPT
DB-GPT is an open-source agentic AI data assistant. It connects to databases, CSV and Excel files, warehouses, and knowledge bases, and lets users ask questions in natural language. The assistant can write and run SQL and Python code, load reusable skills for domain-specific tasks, and produce charts, dashboards, HTML reports, and analysis summaries. The source describes running code and tools in sandboxed environments.
The project is also a platform for building AI-native data agents, workflows, and applications. It names agents, AWEL, RAG, and multi-model support as its building blocks. The quick start examples use API keys for model providers such as OpenAI, Moonshot, and MiniMax. Pricing is not stated on the source page.
Key features
- Connects to databases, CSV and Excel files, warehouses, and knowledge bases
- Converts natural-language questions into SQL queries
- Runs Python and code-driven analysis workflows
- Loads and reuses skills for domain-specific analysis tasks
- Generates charts, dashboards, HTML reports, and analysis summaries
- Runs code and tools in sandboxed environments
- Open source, with source code in a public GitHub repository
- Works across structured and unstructured sources, including databases, spreadsheets, documents, and knowledge bases
- Describes isolated environments for running code and tools
- The quick start examples depend on API keys for external model providers such as OpenAI, Moonshot, or MiniMax
- The one-line installer is listed for macOS and Linux only
DB GPT at a glance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
DB GPT alternatives
Tools and sites you could use instead, ranked by how closely they match.
Open-RAG-Eval evaluates retrieval-augmented generation without requiring golden answers.
Vearch provides distributed vector search capabilities for applications built around artificial intelligence.
MinerU converts complex PDF and Office documents into Markdown or JSON for AI workflows.
RagTune helps inspect, debug, benchmark, and tune retrieval for retrieval augmented generation systems.
AutoRAG helps an agent search for information across files on a computer.
Popular in AI Data & Analytics
Well-known listings from the same topic.
DB GPT FAQ
Which operating systems does the one-line installer support?
Do the quick start examples require an API key?
Tell us and an editor will check it.
Claim the listing and suggest updates yourself. An editor checks every claim first.












