Back to Guides

Managing AI Agents

Create specialised AI assistants for different teams, channels, and use cases

Estimated time: 10-15 minutes

What Are Agents?

Agents are the core of your OpenClaw setup. Each agent is a specialised AI assistant that handles messages from specific communication channels. You can have multiple agents — one for customer support, another for your development team, and a casual assistant for general questions.

Multi-Agent Routing

Route messages from different channels, teams, or groups to specialised agents

Custom Personas

Give each agent a unique personality, tone, and behaviour through workspace files

Model Flexibility

Assign different AI models to different agents — use Claude for support, GPT for coding

Tool Policies

Control what each agent can do — from minimal chat to full coding and file access

1

Step 1: Open the Agents Dashboard

Navigate to the Agents page in SetupClaw APP.

  1. aOpen SetupClaw APP
  2. bClick "Agents" in the sidebar navigation
  3. cThe Agents dashboard shows all your configured agents, their status, and routing bindings
2

Step 2: Create a New Agent

Use the Agent Builder wizard to create a new agent in 6 steps.

  1. aClick "Create Agent" on the Agents dashboard
  2. bStep 1 — Purpose: Describe what this agent should do (e.g., "Handle customer support queries")
  3. cStep 2 — Template: Choose from 4 built-in templates (Support, Developer, Casual, Professional)
  4. dStep 3 — Config: Set the agent name, ID, emoji, AI model, and tool profile
  5. eStep 4 — Channels: Select which channels this agent should respond to
  6. fStep 5 — Persona: Edit the SOUL.md file to define the agent's personality and behaviour
  7. gStep 6 — Deploy: Review and deploy your agent
3

Step 3: Configure Route Bindings

Route bindings determine which messages go to which agent. They use a priority-based matching system.

  1. aOn the agent card, click "Bindings"
  2. bAdd a binding by selecting a channel (e.g., Feishu, DingTalk, Discord)
  3. cOptionally narrow the binding: specific account, group, DM, or team
  4. dBindings are matched in priority order: exact peer > guild+roles > account > channel > default

The "main" agent is the default fallback — any message that doesn't match a specific binding goes here.

4

Step 4: Customise the Persona

Each agent has a workspace with 8 markdown files that define its behaviour.

  1. aOn the agent card, click "Persona"
  2. bEdit the workspace files using the tabbed editor
FilePurposeRequired
SOUL.mdCore personality, values, and communication styleOptional
AGENTS.mdWorkspace guidelines, session rules, and red linesOptional
IDENTITY.mdName, emoji, avatar, and visual themeOptional
TOOLS.mdTool usage notes and configuration hintsOptional
USER.mdUser context and preferencesOptional
HEARTBEAT.mdPeriodic task checklist for automated check-insOptional
MEMORY.mdLong-term curated memories (DM sessions only)Optional
BOOTSTRAP.mdFirst-run onboarding (auto-deleted after setup)Optional
5

Step 5: Set Tool Policies

Control what each agent can do by setting a tool profile.

  1. aOn the agent card, click "Tools"
  2. bChoose a tool profile: Minimal (chat only), Coding (code execution), Messaging (send messages), or Full (all capabilities)
  3. cOptionally add specific tools to the allow or deny list
  4. dEnable sandbox mode for untrusted code execution
  5. eToggle elevated permissions if the agent needs admin access
6

Step 6: Monitor Agent Health

The Agents dashboard shows real-time status for all your agents.

  1. aGreen badge = agent is active and healthy
  2. bYellow badge = agent is degraded (missing workspace files or offline channels)
  3. cRed badge = agent is offline (model not reachable or gateway down)
  4. dCheck the System Health panel for gateway status, channel connectivity, and memory index
  5. eView the Activity & Usage panel for token counts and daily costs

Built-in Agent Templates

🎯

Support Agent

Professional customer-facing assistant with empathetic communication style

💻

Developer Assistant

Technical coding assistant with full tool access and code execution

😊

Casual Assistant

Friendly general-purpose assistant for everyday questions

👔

Professional Assistant

Formal business assistant for executive communication

Advanced Features

Sub-Agents

Configure agents that can call other agents for specialised tasks. Set up a supervisor agent that delegates to support and escalation agents.

Heartbeat Tasks

Schedule periodic automated tasks. Your agent can check emails, scan for updates, or run reports on a schedule.

Memory Search

Enable long-term memory using vector-based search. Your agent remembers conversations and can recall relevant context.

Model Fallbacks

Set a chain of fallback models. If Claude is unavailable, the agent automatically falls back to GPT, then to Gemini.

Troubleshooting