agent-graph

English | 中文

⚠️ Project Status: This project is currently on pause and will not receive new feature updates. The online demo service has been discontinued.

⚠️ 项目状态：本项目目前处于暂停更新状态，不会再更新新功能。在线体验服务已下线。

Agent-Graph is a Multi-Agent System built on the principles of Context Engineering. It integrates Sub-agent, Long-term Memory, MCP, Agent-based Workflow, and other capabilities. By integrating Context Engineering best practices into a visual development experience, Agent-Graph enables developers to rapidly build, test, and deploy complex multi-agent applications.

Table of Contents

1. Framework
2. Deployment Guide
   • Clone Project
   • Configure and Start Docker Services
   • Deploy Backend
   • Access Application
3. Core Features
4. Future Roadmap
   • Coming Soon
   • Future Plans
5. Frontend Feature Showcase
6. Citation
7. WeChat Group

1. Framework

System Architecture

User Journey

2. Deployment Guide

📖 Detailed Installation Documentation: docs/first-steps/install.md

System Requirements

Quick Start

2.1. Clone Project

git clone https://github.com/keta1930/agent-graph.git
cd agent-graph

2.2. Configure and Start Docker Services

cd docker/agent_graph_services
cp .env.example .env
# Edit .env file to configure necessary parameters (see installation documentation)
docker-compose up -d

Service Addresses:

• MongoDB Express (Database Management): http://localhost:8081
• MinIO Console (File Storage): http://localhost:9011

2.3. Deploy Backend

Using uv (Recommended):

cd ../..  # Return to project root
uv sync
cd agent_graph
uv run python main.py

Using pip:

cd ../..  # Return to project root
pip install -r requirements.txt
cd agent_graph
python main.py

Run in Background:

nohup python main.py > app.log 2>&1 &

2.4. Access Application

Open browser and visit: http://localhost:9999

Login Page (Admin login with username and password configured in .env):

Registration Page (New users can register with invitation code):

Other Access Endpoints:

• API Documentation: http://localhost:9999/docs
• Health Check: http://localhost:9999/health

Frontend Development (Optional)

If you need to modify frontend code:

cd frontend
npm install
npm run dev  # Development server: http://localhost:5173
npm run build  # Build production version

Note: The repository includes pre-built frontend files. This step is only needed when developing or customizing the frontend.

3. Core Features

Core Components

Workflow Capabilities

Extension Capabilities

Collaboration & Management

4. Future Roadmap

📖 Complete Roadmap: docs/roadmap/index.md

The platform continues to evolve, bringing more powerful Agent capabilities and better collaboration experiences to users.

Recently Implemented

The following features have been recently implemented and are now available:

Coming Soon

The following features are coming soon or actively under development:

Future Plans

These features are under continuous exploration and planning:

5. Frontend Feature Showcase

5.1. Chat Welcome Page

Entry interface for starting conversations with Agents, supporting quick selection of preset Agents or creating new conversations.

5.2. Workspace - Agent Management

Create, configure, and manage agents, set system prompts, tools, and model parameters.

5.3. Workspace - Workflow Management

Visual drag-and-drop workflow designer, supporting multiple node types and complex process orchestration.

5.4. Workspace - Model Management

Configure and manage multiple LLM models, set API Keys and model parameters.

5.5. Workspace - System Toolbox

View and configure built-in system tools, including resource creation and collaboration tools.

5.6. Workspace - MCP Management

Manage MCP server connections, configure external tool and data source integrations.

5.7. Workspace - Prompt Management

Centrally manage reusable Prompt templates, supporting categorization and version control.

5.8. Workspace - File Management

Manage uploaded files and attachments, supporting file preview and organization.

5.9. Workspace - Memory Management

View and manage Agent's long-term memory and knowledge base.

6. Citation

If you find Agent-Graph helpful for your research or work, please consider citing it:

@misc{agent_graph_2025,
  title        = {agent-graph},
  author       = {Yan Yixin},
  howpublished = {\url{https://github.com/keta1930/agent-graph}},
  note         = {Accessed: 2025-04-24},
  year         = {2025}
}

7. Contact

For questions, suggestions, or collaboration inquiries, feel free to reach out:

📧 Email: [email protected]