apconw/Aix-DB

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

What it solves

Aix-DB lets business users ask data questions in natural language and instantly get answers, SQL queries, and visual charts, removing the need to write code or know database schemas.

How it works

The system uses a large language model (LLM) to understand user intent, then a RAG‑based retrieval layer enriches the request with schema knowledge. A Text‑to‑SQL agent generates and validates SQL, which is run against one of many supported databases. Results are automatically visualized with ECharts/AntV in a Vue‑based web UI. The architecture is layered: a Vue 3 front‑end, a Sanic API gateway, an intelligent service layer (LLM, Text2SQL, RAG, multi‑agent MCP), and storage back‑ends (relational, vector, graph, file).

Who it’s for

  • Business analysts and product managers who need quick data insights without SQL expertise.
  • Developers looking for a plug‑and‑play conversational BI platform that can be self‑hosted.
  • Enterprises that want a secure, on‑premise solution for natural‑language data exploration.

Highlights

  • End‑to‑end natural‑language to data insight flow (ChatBI).
  • Supports 8+ relational databases and various file sources.
  • Multi‑agent MCP framework for extensible skill integration.
  • Built‑in visual dashboard, report center, and conversational chart editing.
  • Deployable via Docker or Docker‑Compose with optional local development setup.
  • Open‑source Apache 2.0 license with a commercial Pro edition for enterprise features.

Related

  • Project
    dataease/SQLBot

    An intelligent data querying system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language into SQL and visual charts.

  • Project
    zhongyu09/openchatbi

    OpenChatBI is an open‑source, LLM‑driven chat interface for business intelligence. It turns natural‑language questions into SQL, runs them against your data warehouse, and returns results with Plotly visualisations. Built on LangGraph/LangChain, it includes a data‑catalog, optional vector retrieval, forecasting, anomaly detection, Python code execution, persistent conversation memory, and optional human‑in‑the‑loop gating. Install via `uv sync` or `pip`, configure LLM and database credentials, and launch the provided Gradio or Streamlit UI.

  • Project
    DeepInsight-AI/DeepBI

    An AI-native data analysis platform that uses LLMs to allow users to explore, query, and visualize data from multiple sources via natural language conversations.

  • Project
    OtterMind/Chat2DB

    An AI-powered database client and SQL workspace that allows developers and analysts to generate, explain, and optimize SQL using natural language.

  • Project
    Zafer-Liu/Data-Analysis-Agent

    Data‑Analysis‑Agent is a Flask‑based AI agent that turns natural‑language questions into SQL queries, runs them on uploaded files or connected databases, auto‑generates Plotly visualisations, and returns business insights. It works with any OpenAI‑compatible LLM, supports many chart types, and offers Windows installers, cross‑platform zip, or script‑based installation.