Phase 7 / Ep 32: Build Your Agent Legion — Multi-Agent Architecture with Specialized Division of Labor

🎯 Learning Objective: Design and deploy multi-Agent collaboration systems.

1. Four Major Agent Architectures

graph TB
    subgraph Channels["User Entry Points"]
        TG["📱 Telegram"]
        DC["💬 Discord"]
        CLI["💻 CLI"]
    end

    subgraph Agents["Agent Legion"]
        PA["🧑‍💼 Personal Agent\nprofile: basic\nDaily Conversation · Reminders · Schedule"]
        CA["💻 Code Agent\nprofile: coding\nDevelopment · Testing · Deployment"]
        OA["🔧 Ops Agent\nprofile: full（in container）\nOperations · Monitoring · Alerting"]
        RA["📚 Research Agent\nprofile: standard\nReading · Summarizing · Translation"]
    end

    TG --> PA
    DC -->|"#dev"| CA
    DC -->|"#ops"| OA
    CLI --> CA
    CLI --> RA

2. Create All Agents

# Create Agent (personal already exists by default)
openclaw agents add code-agent
openclaw agents add ops-agent
openclaw agents add research-agent

# Set Permissions
openclaw agents config personal tools.profile basic
openclaw agents config code-agent tools.profile coding
openclaw agents config ops-agent tools.profile full
openclaw agents config research-agent tools.profile standard

# Bind Channels
openclaw agents bind personal telegram
openclaw agents bind code-agent cli
openclaw agents bind code-agent discord --channel dev
openclaw agents bind ops-agent discord --channel ops
openclaw agents bind research-agent cli

3. Agent Collaboration

Agents can call each other:

You (Telegram) → Personal Agent: "Help me research the new features of OpenClaw v4"
Personal Agent → Research Agent: "Please search for OpenClaw v4 changelog and summarize"
Research Agent → Personal Agent: "Summary complete: 1. Added XXX 2. Optimized YYY..."
Personal Agent → You (Telegram): "Research results:..."

4. Design Principles

Next Episode Preview: Ep 33, Customize Agent's personality and code of conduct via SOUL.md.