agent-pard0x/multi-agent-supervisor/README-modular.md

Multi-Agent Sysadmin Assistant

A modular multi-agent system for system administration tasks using LangChain and LangGraph.

Architecture

The system is organized into several modules for better maintainability:

📁 Project Structure

multi-agent-supervisor/
├── main-multi-agent.py      # Main entry point
├── config.py                # Configuration and settings
├── supervisor.py            # Supervisor orchestration
├── utils.py                 # Utility functions
├── requirements.txt         # Dependencies
├── custom_tools/            # Custom tool implementations
│   ├── __init__.py
│   ├── log_tail_tool.py     # Log reading tool
│   └── shell_tool_wrapper.py # Shell tool wrapper
└── agents/                  # Agent definitions
    ├── __init__.py
    ├── system_agents.py     # System monitoring agents
    ├── service_agents.py    # Service-specific agents
    ├── network_agents.py    # Network and security agents
    └── analysis_agents.py   # Analysis and remediation agents

Agents

System Agents

• System Info Worker: Gathers CPU, RAM, and disk usage
• Service Inventory Worker: Lists running services

Service Agents

• MariaDB Analyzer: Checks MariaDB configuration and logs
• Nginx Analyzer: Validates Nginx configuration and logs
• PHP-FPM Analyzer: Monitors PHP-FPM status and performance

Network Agents

• Network Diagnostics: Uses ping, traceroute, and dig
• Certificate Checker: Monitors TLS certificate expiration

Analysis Agents

• Risk Scorer: Aggregates findings and assigns severity levels
• Remediation Worker: Proposes safe fixes for issues
• Harmonizer Worker: Applies system hardening best practices

Benefits of Modular Architecture

1. Separation of Concerns: Each module has a single responsibility
2. Reusability: Tools and agents can be easily reused across projects
3. Maintainability: Easy to update individual components
4. Testability: Each module can be tested independently
5. Scalability: Easy to add new agents or tools
6. Code Organization: Clear structure makes navigation easier

Usage

from supervisor import create_sysadmin_supervisor

# Create supervisor with all agents
supervisor = create_sysadmin_supervisor()

# Run analysis
query = {
    "messages": [
        {
            "role": "user", 
            "content": "Check if my web server is running properly"
        }
    ]
}

result = supervisor.invoke(query)

Adding New Agents

1. Create agent function in appropriate module under agents/
2. Import and add to supervisor in supervisor.py
3. Update supervisor prompt in config.py

Adding New Tools

1. Create tool class in custom_tools/
2. Export from custom_tools/__init__.py
3. Import and use in agent definitions