agent-graph

English | 中文

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.

Documentation	https://keta1930.github.io/agent-graph/

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

Component	Requirement
Operating System	Linux, macOS, or Windows (requires WSL2)
Docker	Version 20.10+ with Docker Compose
Python	Version 3.11+
Memory	Minimum 4GB (8GB recommended)
Storage	At least 10GB available space

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

cp .env.example .env
# Set all blank credentials and secrets before startup
python agent_graph/scripts/generate_jwt_secret.py
docker compose --env-file .env -f docker/docker-compose.yml up -d

Default Service Addresses:

• MongoDB Express (Database Management): http://localhost:20041
• MinIO Console (File Storage): http://localhost:20043

2.3. Deploy Backend

Using uv (Recommended):

uv sync
uv run --env-file .env fastapi run

Using pip:

pip install -r requirements.txt
dotenv -f .env run -- fastapi run

Run in Background:

nohup uv run --env-file .env fastapi run > app.log 2>&1 &

2.4. Access Application

Open the address configured by PUBLIC_API_BASE_URL (default: http://localhost:20050).

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:20050/docs
• Health Check: http://localhost:20050/health

Frontend Development (Optional)

If you need to modify frontend code:

cd frontend
npm install
npm run dev  # Uses FRONTEND_PORT from the root .env
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

Feature	Description	Documentation
Agent	AI entities with capabilities to understand goals, use tools, iterate optimization, maintain context and long-term memory, solving open-ended tasks through autonomous action execution	Agent Docs
Graph (Workflow)	Orchestrate multiple agents into structured workflows, defining execution flow through nodes and edges, suitable for predictable multi-stage tasks	Graph Docs
Model	Support for LLM and VLM models (OpenAI compatible), flexible API Key configuration	Model Docs
Memory	Short-term memory maintains conversation context, long-term memory stores user preferences and Agent knowledge base across sessions	Memory Docs
Prompt Center	Centralized management of reusable Prompt templates, supporting categorization, import/export, and cross-project references	Prompt Docs
Projects	Organize conversations into collections with shared files	Projects Docs

Workflow Capabilities

Feature	Description	Documentation
Visual Graph Editor	Frontend drag-and-drop workflow design, supporting linear, parallel, conditional, and nested graph types, WYSIWYG	Graph Docs
Subgraph Nesting	Use entire Graphs as single nodes for nesting, enabling modular, reusable, and hierarchical workflow construction	Subgraph Docs
Handoffs (Smart Routing)	Nodes dynamically select next execution node, supporting intelligent decisions, conditional branching, and iterative optimization loops	Handoffs Docs
Task (Scheduling)	Scheduled or periodic automatic Graph execution, supporting cron expressions, concurrent instances, and execution history tracking	Task Docs

Extension Capabilities

Feature	Description	Documentation
MCP Protocol Integration	Connect external tools and data sources (databases, APIs, file systems, cloud services, etc.) through standardized protocol, connect once and use everywhere	MCP Docs
Built-in Tool Set	Provides resource creation (Agent Creator, Graph Designer, MCP Builder, Prompt Generator, Task Manager), collaboration (Sub-agent, File Tool), and query (Memory Tool, System Operations) system tools	Tools Docs

Collaboration & Management

Feature	Description	Documentation
Team Collaboration	Admins create invitation codes, manage team members, assign role permissions (Super Admin, Admin, Regular User)	Team Management
Conversation Management	Support conversation history viewing, file attachment management, and session context maintenance	Quick Start

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:

Feature	Core Value	Documentation
Multimodal Support	VLM gives Agents visual understanding capabilities	Details
Projects	Organize conversations into collections with shared resources	Details

Coming Soon

The following features are coming soon or actively under development:

Feature	Core Value	Documentation
Team Resource Sharing	Share Agents, workflows, and Prompts within teams	Details
Agent Skills	Progressive context engineering to improve efficiency and capabilities	Details

Future Plans

These features are under continuous exploration and planning:

Feature	Core Value	Documentation
External Agent API	Open Agents to external calls, building a service ecosystem	Details
User Analytics	Effect evaluation and team insights	Details

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: yandeheng1@gmail.com