Zafer-Liu/Data-Analysis-Agent

🚀你的私人数据分析助手。通过对话式交互，自动生成可视化报表与商业洞察，让数据决策变得像聊天一样简单。 🚀 Your personal data analysis assistant. Say goodbye to complex SQL and Excel formulas. An LLM-powered data analysis agent. Chat with your data to instantly generate visualizations and business insights. Making data-driven decisions has never been easier.

What it solves

It enables non-technical users to perform complex business data analysis using natural language instead of writing SQL queries or manually building charts. It bridges the gap between raw data sources (files or databases) and actionable business insights by automating the technical pipeline of data retrieval and visualization.

How it works

Users connect a data source and ask questions in plain language. The agent then executes a multi-step process:

  1. Intent Understanding: Interprets the user's request.
  2. Schema Analysis: Identifies the structure of the connected data.
  3. SQL Generation: Automatically writes and executes the necessary SQL query.
  4. Visualization: Recommends and generates the most appropriate chart from a library of 43 types across 6 categories.
  5. Insight Generation: Provides a business summary of the findings.

This process is delivered via Server-Sent Events (SSE) for real-time transparency. The system is compatible with various LLMs (DeepSeek, OpenAI, AtlasCloud) and supports extensions via MCP (Model Context Protocol) and a custom business knowledge base.

Who it’s for

  • Business analysts and managers who need quick data insights without SQL knowledge.
  • Users who want to automate the generation of business reports (Excel, Word, PPT).
  • Teams using Feishu (Lark) who want to integrate data analysis directly into group chats via a bot.

Highlights

  • Multi-Source Connectivity: Supports Excel, CSV, SQLite, MySQL, PostgreSQL, and SQL Server.
  • Extensive Visualization: Automatically selects from 43 different chart types (e.g., Sankey, Treemap, Violin plots).
  • Advanced Analytics: Includes built-in tools for K-Means clustering, decision tree modeling, and outlier handling (trimming/winsorizing).
  • Export Capabilities: Generates formatted Excel tables, .docx reports, and PPT presentations.
  • Feishu Integration: Can read Feishu multi-dimensional tables and return analysis results directly to chat groups.

Related

  • Project
    Tswoen/Paper-Agent

    Paper‑Agent is an open‑source AI research assistant that automates literature review creation. It uses a LangGraph‑driven workflow of specialized agents (search, read, analyse, outline, write) that call LLMs (OpenAI/Anthropic compatible) to retrieve papers from arXiv, OpenAlex, and Semantic Scholar, download PDFs, convert them to markdown, chunk and embed the text in ChromaDB, analyse sub‑topics, generate a structured outline, and write each section of a review. A FastAPI backend streams real‑time progress via SSE, persisting sessions in SQLite + files, while a Vue 3 front‑end lets users configure model providers, monitor token usage, and resume work after refresh. Installation uses the `uv` Python package manager and npm for the UI; configuration is done via `config/model.json`. The project is fully open source and invites contributions via tests and PRs.

  • Project
    modelscope/ms-agent

    MS‑Agent is a lightweight Python framework for building autonomous LLM agents with tool‑calling, memory, multimodal input, and a skill‑retrieval system. It uses ModelScope’s Model Calling Protocol (MCP) for LLM access, provides a React/FastAPI web UI, and includes ready‑made projects for code generation, short video creation, and deep‑research workflows.

  • Project
    AMA-CMFAI/LAMBDA

    A data analysis agent that converts natural-language questions into reproducible analysis workflows, including code execution, visualization, and report generation.

  • Project
    zhayujie/CowAgent

    CowAgent is an open‑source, multi‑modal AI assistant platform. It receives messages from many chat channels, uses a chosen LLM to plan and reason, accesses a rich set of system tools and user‑defined “skills”, and maintains a three‑tier memory plus an auto‑curated knowledge base. Installable via a one‑line script or Docker, it supports dozens of LLM providers and runs on a personal computer or server.

  • Project
    deepagent-ltd/deepagent-code

    DeepAgent Code is a self‑hosted AI coding workspace that combines a large‑language‑model runtime with durable, versioned project memory, live planning, multi‑agent collaboration, and fine‑grained human control. It offers three collaboration modes (Auto, Loop, Design), integrates LSP‑based code intelligence, plug‑in domain packs, and an expert‑panel review system, and works with any of 75+ model providers. Install via a one‑line script, configure providers through a UI or CLI, and run tasks like `deepagent-code run "add rate limiting to /api/users"`. The code is AGPL‑3.0‑or‑later and built on Bun.