Sponsored by Deepsite.site

EFFLUX.AI

创建者
a year ago
Open-Source General-Purpose AI Agent Platform** This project aims to build an open-source general-purpose AI Agent platform, providing end-to-end autonomous task execution, tool invocation, and virtual sandbox support through the following three core projects, empowering enterprises and individuals to efficiently achieve AI productivity: 1. **[efflux-desktop](https://github.com/isoftstone-data-intelligence-ai/efflux-desktop)**: Offers desktop application support, enabling users to manage and operate locally. 2. **[efflux-frontend](https://github.com/isoftstone-data-intelligence-ai/efflux-frontend)**: Implements a user-friendly interface for task configuration and result visualization. 3. **[efflux-backend](https://github.com/isoftstone-data-intelligence-ai/efflux-backend)**: Provides core logic and task scheduling capabilities, supporting tool invocation and virtual sandbox execution. By integrating these three projects, the platform enables efficient AI task management and automation, delivering powerful AI productivity support for enterprises and individuals. --- ### **Key Features** - **Autonomous Task Execution**: Supports end-to-end automation from task configuration to execution. - **Tool Invocation**: Integrates various tools, allowing flexible extension and invocation. - **Virtual Sandbox**: Provides a secure and isolated execution environment, ensuring task safety and stability. --- ### **Use Cases** - AI process automation within enterprises. - Developers’ integration and extension of AI tools. - Personal AI task automation management.
内容

🚀 Project Overview

Efflux — An AI Copilot built for super-individuals.

Efflux Desktop integrates multi-vendor models and tool invocation capabilities, supporting command-based tool access and plugin extensions. Designed for real-world tasks, Efflux brings human-AI collaboration back under your control — amplifying the judgment and execution power of super-individuals.

It doesn’t decide for you — it helps you stay in control.

✨ Core Features

LLM-powered Conversations

  • Multi-vendor AI model integration (OpenAI, Anthropic, DeepSeek, etc.)

  • Natural-language-based conversations

  • Text-to-artifact capabilities

  • Real-time streaming chat responses

  • Chat history management

 Tool Integration and Calling

  • Dynamic discovery and loading of MCP servers

  • Tool configuration management support

  • Exception handling and timeout control

  • Standardized tool calling interface

Supported OS

  • Windows

  • macOS

🚀 Quick Start

After installing the executable file and launching Efflux Desktop, you can start your AI journey by following the following steps.

Configure Your Models

  1. In the navigation pane of Efflux Desktop, select Models.

  2. In the Model Providers page, find your desired vendor card, and click API-KEY.

  3. In the pop-up dialog, enter your endpoint and API key, and click Save.

Install Plugins

If you want to use existing MCP servers to complete your task, do the following:

  1. In the navigation pane, select Plugins.

  2. In the Discover Plugins tab, click Add Custom Plugin.

  3. In the pop-up dialog, do either of the following and click Add.

    1. enter the plugin name, command, environment variables, and arguments (if any), or 

    2. if you've already got a JSON string, select JSON Mode and paste it.

Tip

Leverage the following resources of MCP server to unlock more automation capabilities.

https://mcp.so/

https://mcpmarket.cn/

https://mcp-servers-hub-website.pages.dev/

Start Your Conversation

  1. In the navigation pane, select Chat.

  2. In the chatbox, select the model you've configured, and:

    1. tell Efflux your question, or

    2. switch to the Build mode and describe what you want Efflux to build.

  3. To use the installed plugin, enter the @ sign and select the target one.

  4. Press the Enter key to start your conversation.

🏗️ Project Architecture

Directory Structure

efflux-desktop/
├── adapter/          # Adapter layer
│   ├── mcp/          # MCP protocol adapters
│   ├── model_sdk/    # Model SDK adapters
│   ├── persistent/   # Persistence adapters
│   └── web/          # Web interface adapters
├── application/      # Application layer
│   ├── domain/       # Domain objects
│   ├── port/         # Port interfaces
│   └── service/      # Application services
├── common/           # Common components
│   ├── core/         # Core infrastructure
│   └── utils/        # Utility classes
└── main.py           # Application entry point

🔧 Development Guide

1. Clone the Project

git clone https://github.com/isoftstone-data-intelligence-ai/efflux-desktop.git
cd efflux-desktop

2. Install Dependencies

Install dependencies using uv package manager:

pip install uv
uv sync --reinstall

3. Activate virtual environment

Activate a virtual environment and configure environment variables.

# Activate virtual environment
source .venv/bin/activate   # MacOS/Linux

# Deactivate when needed
deactivate

4. Start the Service

uv run

The service will start at http://127.0.0.1:8000.

API Usage Examples

POST /api/agent/chat/default_chat
Content-Type: application/json

{
  "firm": "openai",
  "model": "gpt-4",
  "system": "You are a helpful AI assistant",
  "query": "Hello, please introduce yourself",
  "mcp_name_list": ["example-server"]
}

🤝 Contributing

  1. Fork this project.

  2. Create a feature branch (git checkout -b feature/AmazingFeature).

  3. Commit your changes (git commit -m 'Add some AmazingFeature').

  4. Push to the branch (git push origin feature/AmazingFeature).

  5. Submit a Pull Request.

📄 License

This project follows the appropriate open source license. Please refer to the LICENSE file for details.

🆘 Support & Help

For questions or suggestions, please contact us through:

  • Submit Issues

  • Start Discussions

推荐的 MCP Client
TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.
WindsurfThe new purpose-built IDE to harness magic
CursorThe AI Code Editor
Refact.aiOpen-source AI Agent for VS Code and JetBrains that autonomously solves coding tasks end-to-end.
MCP ConnectEnables cloud-based AI services to access local Stdio based MCP servers via HTTP requests
Continue⏩ Create, share, and use custom AI code assistants with our open-source IDE extensions and hub of models, rules, prompts, docs, and other building blocks
A Sleek AI Assistant & MCP Client5ire is a cross-platform desktop AI assistant, MCP client. It compatible with major service providers, supports local knowledge base and tools via model context protocol servers .
ZedCode at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
Visual Studio Code - Open Source ("Code - OSS")Visual Studio Code
chatmcpChatMCP is an AI chat client implementing the Model Context Protocol (MCP).
EXPLYT
Roo Code (prev. Roo Cline)Roo Code (prev. Roo Cline) gives you a whole dev team of AI agents in your code editor.
y-cli 🚀A Tiny Terminal Chat App for AI Models with MCP Client Support
ChatWiseThe second fastest AI chatbot™
Cline – #1 on OpenRouterAutonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
LutraLutra is the first MCP compatible client built for everyone
Cherry Studio🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.
HyperChatHyperChat is a Chat client that strives for openness, utilizing APIs from various LLMs to achieve the best Chat experience, as well as implementing productivity tools through the MCP protocol.
Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.
DeepChatYour AI Partner on Desktop
MCP PlaygroundCall MCP Server Tools Online