#21 · Primary category： LLM Application Frameworks
DB-GPT
open-source agentic AI data assistant for the next generation of AI + Data products.
Project last updated：08/28/26
GitHub Stars
19.8K
Forks
2.9K
Contributors
200
License
MIT
Why we included this project
DB-GPT bundles the pieces that data-facing AI applications usually need into one framework: database, spreadsheet, and warehouse connections, natural-language-to-SQL, sandboxed code execution, and chart and report generation, all tied together with a workflow orchestration layer and a multi-agent runtime. Teams that want a private, self-hosted data assistant rather than sending data to external APIs will find the multi-model management and privacy features directly useful. It also ships a ready-to-run assistant interface, so you can start with the built-in app and extend it with custom skills and agents. The trade-off is that it is a fairly large framework, so expect a real setup and learning curve before it pays off.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform