Super Agent Party

What is Super Agent Party

super-agent-party is a project that transforms a large model into an intelligent agent capable of accessing knowledge repositories, connecting to the internet, utilizing MCP services, and performing deep thinking and research. It can be used directly via OpenAI API calls or through web and desktop applications.

Use cases

Use cases include automated customer support agents, research assistants that gather and analyze data, educational tools that provide personalized learning experiences, and any application requiring advanced reasoning and information access.

How to use

To use super-agent-party, integrate it with your application by utilizing the OpenAI API or by deploying it on web and desktop platforms. Follow the setup instructions in the README to configure knowledge bases, internet connectivity, and MCP services.

Key features

Key features include: 1) Knowledge Base access for answering questions; 2) Internet Connectivity for proactive information searches; 3) MCP Services for calling relevant services; 4) Deep Thinking capabilities for enhanced reasoning and analysis.

Where to use

super-agent-party can be used in various fields such as education, research, customer support, and any domain requiring intelligent information retrieval and processing.

Introduction

🚀 Zero Intrusion · Minimalist Expansion · Empower LLM APIs with Enterprise-Grade Capabilities without modifying a single line of code, seamlessly add advanced features to your LLM interfaces, including knowledge base integration, real-time internet access, permanent memory, code execution tools, MCP, A2A, deep thinking control, in-depth research, visual understanding, image generation, custom tools, and more. Build a plug-and-play LLM enhancement middleware platform. At the same time, you can deploy your agent configuration to social platforms with just one click (official QQ bot is already supported).You can also use the workflows built on other intelligent platform as tools for intelligent agents (comfyui is already supported).

Why Choose Us?

• ✅ Efficient development: Supports streaming output, does not affect the original API’s response speed, and no code changes are required
• ✅ Quick access: Avoids repeated access to multiple service providers for a single function, pre-configured with mainstream LLM manufacturer/intelligent body protocol adapters, compatible with OpenAI/Ollama/MCP/A2A, and experience the next-generation LLM middleware instantly
• ✅ High customization: Supports advanced agent features such as custom knowledge base, real-time internet access, permanent memory, code execution tools, MCP, A2A, deep thinking control, in-depth research, visual capabilities, image generation, and custom tools, allowing you to build a plug-and-play LLM enhancement middleware platform.
  Customized agents can be saved as snapshots for easy reuse in the future. The snapshot agents can be directly called using the OpenAI API.
• ✅ Data security: Supports local knowledge base and local model access, ensuring data is not leaked and enterprise data security is maintained. All files will be cached locally and will not be uploaded anywhere.
• ✅ Team collaboration: Supports team collaboration, multi-person sharing of knowledge base, model services, tools, MCP, A2A, and other resources, improving team collaboration efficiency. Chat records or files and images in the knowledge base are stored locally and can be used as a local file bed or image bed.
• ✅One-click deployment: Supports one-click deployment to social software, such as QQ, making it convenient for users to use the intelligent entity anytime and anywhere.

Quick Start

Windows Desktop Installation

👉 Click to download

⭐ Note! Choose to install only for the current user during installation, otherwise, administrator privileges will be required to start.

MacOS Desktop Installation (beta test)

👉 Click to download

⭐ Note! After downloading, drag the app file from the dmg file to the /Applications directory. Then open the Terminal and execute the following command, entering the root password when prompted, to remove the Quarantine attribute added due to being downloaded from the internet:

sudo xattr -dr com.apple.quarantine /Applications/Super-Agent-Party.app

Linux Desktop Installation

We provide two mainstream Linux installation package formats for your convenience in different scenarios.

1. Install using .AppImage (Recommended)

.AppImage is a Linux application format that does not require installation and can be used immediately. Suitable for most Linux distributions.

👉 Click to download

2. Install using .deb package (Suitable for Ubuntu/Debian systems)

👉 Click to download

Docker Deployment (Recommended)

• Two commands to install this project:

  docker pull ailm32442/super-agent-party:latest
  docker run -d -p 3456:3456 -v ./super-agent-data:/app/data ailm32442/super-agent-party:latest
  

• ⭐Note! ./super-agent-data can be replaced with any local folder, after Docker starts, all data will be cached in this local folder and will not be uploaded anywhere.

• Plug and play: access http://localhost:3456/

Source Code Deployment

• Windows:

  git clone https://github.com/heshengtao/super-agent-party.git
  cd super-agent-party
  uv sync
  npm install
  start_with_dev.bat
  

• Linux or Mac:

  git clone https://github.com/heshengtao/super-agent-party.git
  cd super-agent-party
  uv sync
  npm install
  chmod +x start_with_dev.sh
  ./start_with_dev.sh
  

Usage

• Desktop: Click the desktop icon to use immediately.

• Web or docker: Access http://localhost:3456/ after startup.

• API call: Developer-friendly, perfectly compatible with OpenAI format, can output in real-time, and does not affect the original API’s response speed. No need to modify the calling code:

  from openai import OpenAI
  client = OpenAI(
    api_key="super-secret-key",
    base_url="http://localhost:3456/v1"
  )
  response = client.chat.completions.create(
    model="super-model",
    messages=[
        {"role": "user", "content": "What is Super Agent Party?"}
    ]
  )
  print(response.choices[0].message.content)
  

• MCP call: After starting, you can invoke the local MCP service by writing the following content in the configuration file:

Features

Please refer to the following document for the main functions:

• 👉 Chinese document
• 👉 English document

Disclaimer:

This open-source project and its content (hereinafter referred to as the “project”) are for reference only and do not imply any explicit or implicit warranties. The project contributors do not assume any responsibility for the completeness, accuracy, reliability, or applicability of the project. Any behavior that relies on the project content shall be at the user’s own risk. In any case, the project contributors shall not be liable for any indirect, special, or incidental losses or damages arising from the use of the project content.

License Agreement

This project uses a dual licensing model:

1. By default, this project follows the GNU Affero General Public License v3.0 (AGPLv3) license agreement
2. If you need to use this project for closed-source commercial purposes, you must obtain a commercial license from the project administrator

Using this project for closed-source commercial purposes without written authorization is considered a violation of this agreement. The complete text of AGPLv3 can be found in the LICENSE file in the project root directory or at gnu.org/licenses.

Support:

Follow us

Join the Community

If you have any questions or issues with the project, you are welcome to join our community.

1. QQ Group: 931057213

2. WeChat Group: we_glm (add the assistant’s WeChat and join the group)

3. Discord: Discord link

Donate

If my work has brought value to you, please consider buying me a cup of coffee! Your support not only injects vitality into the project but also warms the creator’s heart. ☕💖 Every cup counts!