Here are a few options, prioritizing clarity and SEO: * **MaxKB: Enterprise AI assistant w/ RAG, workflows, & MCP tool use. Open-source.** (75 characters) * **MaxKB: Open-source AI assistant for

17,000
2,201
<p align="center">
  <img src="https://github.com/1Panel-dev/maxkb/assets/52996290/c0694996-0eed-40d8-b369-322bf2a380bf" alt="MaxKB" width="300" />
</p>

<h3 align="center">An Open-Source AI Assistant for Enterprise</h3>

<p align="center">
  <a href="https://trendshift.io/repositories/9113" target="_blank">
    <img src="https://trendshift.io/api/badge/repositories/9113" alt="1Panel-dev%2FMaxKB | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/>
  </a>
</p>

<p align="center">
  <a href="https://www.gnu.org/licenses/gpl-3.0.html#license-text">
    <img src="https://img.shields.io/github/license/1Panel-dev/maxkb?color=%231890FF" alt="License: GPL v3">
  </a>
  <a href="https://github.com/1Panel-dev/maxkb/releases/latest">
    <img src="https://img.shields.io/github/v/release/1Panel-dev/maxkb" alt="Latest release">
  </a>
  <a href="https://github.com/1Panel-dev/maxkb">
    <img src="https://img.shields.io/github/stars/1Panel-dev/maxkb?color=%231890FF&style=flat-square" alt="Stars">
  </a>
  <a href="https://hub.docker.com/r/1panel/maxkb">
    <img src="https://img.shields.io/docker/pulls/1panel/maxkb?label=downloads" alt="Download">
  </a>
  <br/>
  [<a href="/README_CN.md">中文(简体)</a>] | [<a href="/README.md">English</a>]
</p>

<hr/>

**MaxKB (Max Knowledge Brain)** is a powerful and easy-to-use open-source AI assistant designed for enterprise use. It leverages Retrieval-Augmented Generation (RAG) pipelines, robust workflows, and advanced **Model Context Protocol (MCP)** tool-use capabilities. MaxKB is suitable for various applications, including intelligent customer service, corporate internal knowledge bases, academic research, and education.

## Key Features

*   **RAG Pipeline:**
    *   Supports direct document uploading and automatic crawling of online documents.
    *   Features automatic text splitting and vectorization for efficient knowledge indexing.
    *   Significantly reduces hallucinations in large language models (LLMs), providing a more accurate and reliable smart Q&A experience.

*   **Agentic Workflow:**
    *   Equipped with a powerful workflow engine and a rich function library.
    *   Enables orchestration of AI processes to address complex business scenarios.
    *   Leverages **MCP tool-use** for seamless integration and execution of external tools and services within the AI workflow.

*   **Seamless Integration:**
    *   Facilitates rapid, zero-coding integration into third-party business systems.
    *   Quickly equips existing systems with intelligent Q&A capabilities to enhance user satisfaction.

*   **Model-Agnostic:**
    *   Supports a wide range of LLMs, including private models (e.g., DeepSeek, Llama, Qwen) and public models (e.g., OpenAI, Claude, Gemini).

*   **Multi-Modal Support:**
    *   Natively supports input and output of text, images, audio, and video.

## Understanding Model Context Protocol (MCP) in MaxKB

MaxKB utilizes the Model Context Protocol (MCP) to enhance the capabilities of LLMs by allowing them to interact with external tools and services.  MCP provides a standardized way for LLMs to:

*   **Discover Tools:**  LLMs can dynamically discover available tools and their functionalities.
*   **Understand Tool Usage:** MCP provides a clear description of each tool's purpose, input parameters, and expected output.
*   **Execute Tools:**  LLMs can invoke tools with the appropriate parameters and receive results.
*   **Incorporate Results:**  The results from tool execution are seamlessly integrated back into the LLM's context, enabling it to make more informed decisions and provide more accurate responses.

**Benefits of MCP in MaxKB:**

*   **Enhanced Functionality:**  Extends the capabilities of LLMs beyond their inherent knowledge by providing access to real-world data and specialized tools.
*   **Improved Accuracy:**  Reduces reliance on LLM's internal knowledge, leading to more accurate and up-to-date responses.
*   **Increased Automation:**  Automates complex tasks by orchestrating the execution of multiple tools within a workflow.
*   **Greater Flexibility:**  Allows for easy integration of new tools and services, enabling MaxKB to adapt to evolving business needs.

## Quick Start

Execute the script below to start a MaxKB container using Docker:

```bash
docker run -d --name=maxkb --restart=always -p 8080:8080 -v ~/.maxkb:/var/lib/postgresql/data -v ~/.python-packages:/opt/maxkb/app/sandbox/python-packages 1panel/maxkb

Access MaxKB web interface at http://your_server_ip:8080 with default admin credentials:

  • Username: admin
  • Password: MaxKB@123..

For users in China experiencing Docker image pull failures, please refer to the Offline Installation Documentation for installation instructions.

Screenshots

<table style="border-collapse: collapse; border: 1px solid black;"> <tr> <td style="padding: 5px;background-color:#fff;"><img src="https://maxkb.hk/images/overview.png" alt="MaxKB Demo1" /></td> <td style="padding: 5px;background-color:#fff;"><img src="https://maxkb.hk/images/screenshot-models.png" alt="MaxKB Demo2" /></td> </tr> <tr> <td style="padding: 5px;background-color:#fff;"><img src="https://maxkb.hk/images/screenshot-knowledge.png" alt="MaxKB Demo3" /></td> <td style="padding: 5px;background-color:#fff;"><img src="https://maxkb.hk/images/screenshot-function.png" alt="MaxKB Demo4" /></td> </tr> </table>

Technical Stack

Feature Comparison

MaxKB is positioned as a ready-to-use RAG (Retrieval-Augmented Generation) intelligent Q&A application, rather than a middleware platform for building large model applications. The following table is merely a comparison from a functional perspective.

<table style="width: 100%;"> <tr> <th align="center">Feature</th> <th align="center">LangChain</th> <th align="center">Dify.AI</th> <th align="center">Flowise</th> <th align="center">MaxKB <br> (Built upon LangChain)</th> </tr> <tr> <td align="center">Supported LLMs</td> <td align="center">Rich Variety</td> <td align="center">Rich Variety</td> <td align="center">Rich Variety</td> <td align="center">Rich Variety</td> </tr> <tr> <td align="center">RAG Engine</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">✅</td> </tr> <tr> <td align="center">Agent</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td> <td align="center">✅</td> </tr> <tr> <td align="center">Workflow</td> <td align="center">❌</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">✅</td> </tr> <tr> <td align="center">Observability</td> <td align="center">✅</td> <td align="center">✅</td> <td align="center">❌</td> <td align

Repository

1P
1Panel-dev

1Panel-dev/MaxKB

Created

September 14, 2023

Updated

July 7, 2025

Language

Python

Category

AI