Claude + OpenClaw: Complete Setup Guide for Production (2026)

Claude + OpenClaw: Complete Setup Guide for Production (2026)

This guide walks through setting up OpenClaw with Anthropic's Claude models—from initial configuration to production deployment.

Why Claude for OpenClaw

Claude (Sonnet and Opus) is well-suited for agentic workflows:

• Strong instruction following — Reliable execution of complex tasks
• Extended context — 200K tokens for large codebases and documents
• Tool use capabilities — Native support for function calling
• Safety features — Built-in refusals for harmful requests

For most OpenClaw use cases, Claude Sonnet provides the best balance of capability, speed, and cost. Claude Opus is better for complex reasoning tasks where latency is acceptable.

Prerequisites

Before starting:

1. Anthropic API key — Get one at console.anthropic.com
2. OpenClaw installed — Follow the official installation guide
3. Node.js 22+ — Required for OpenClaw

Step 1: Configure Your API Key

Add your Anthropic API key to the OpenClaw configuration.

Option A: Environment variable (recommended)

export ANTHROPIC_API_KEY="sk-ant-..."

Option B: Auth profile via CLI

openclaw configure --section model

The interactive wizard will prompt for your Anthropic credentials. You can also set it directly:

openclaw config set auth.profiles.anthropic:default '{"provider":"anthropic","mode":"api_key"}' --strict-json

Option C: Configuration file

In your ~/.openclaw/openclaw.json:

{
  env: {
    ANTHROPIC_API_KEY: "sk-ant-..."
  }
}

Security note: For production, use environment variables or a secrets manager. Don't commit API keys to version control.

Step 2: Select Your Model

Configure Claude as your primary model:

{
  agent: {
    workspace: "~/.openclaw/workspace",
    model: {
      primary: "anthropic/claude-sonnet-4-5"
    }
  }
}

Or via the CLI:

openclaw config set agent.model.primary "anthropic/claude-sonnet-4-5"

Model options:

Recommendation: Start with Sonnet. Upgrade to Opus only if you hit capability limits.

Want fallbacks? Set a fallback model in case Anthropic has an outage:

{
  agent: {
    model: {
      primary: "anthropic/claude-sonnet-4-5",
      fallbacks: ["anthropic/claude-opus-4-6", "openai/gpt-5.2"]
    }
  }
}

Step 3: Configure Your Agent

Set your agent's identity and workspace:

{
  identity: {
    name: "Clawd",
    theme: "helpful assistant",
    emoji: "🦞"
  },
  agent: {
    workspace: "~/.openclaw/workspace",
    model: { primary: "anthropic/claude-sonnet-4-5" }
  }
}

OpenClaw uses bootstrap files in your workspace to shape agent behavior:

• AGENTS.md — Operating instructions and memory
• SOUL.md — Persona, boundaries, tone
• TOOLS.md — Tool usage notes and conventions

Edit these files to define your agent's personality and expertise. They're injected into the agent context at the start of every session.

Step 4: Configure Tools

Control which tools your agent can use:

{
  tools: {
    allow: ["exec", "read", "write", "edit"],
    deny: ["browser"]
  }
}

Or via the CLI:

openclaw config set tools.allow '["exec","read","write","edit"]' --strict-json
openclaw config set tools.deny '["browser"]' --strict-json

Security principle: Only enable tools your agent actually needs. Disable everything else.

Step 5: Set Up Model Allowlist

Control which models are available for switching via the /model command:

{
  agents: {
    defaults: {
      models: {
        "anthropic/claude-sonnet-4-5": { alias: "sonnet" },
        "anthropic/claude-opus-4-6": { alias: "opus" },
        "openai/gpt-5.2": { alias: "gpt" }
      }
    }
  }
}

This lets you switch between models on the fly without editing config.

Step 6: Test Locally

Start the OpenClaw gateway:

openclaw gateway run

Test with a message:

openclaw message send "What model are you running?"

Expected response should confirm Claude Sonnet.

Check gateway health:

openclaw status

Verify tools work by asking the agent to list files or run a command.

Step 7: Production Configuration

For production, lock down the gateway:

{
  gateway: {
    mode: "local",
    port: 18789,
    bind: "loopback",
    auth: {
      mode: "token",
      token: "your-secure-gateway-token"
    },
    controlUi: { enabled: false }
  },
  agent: {
    workspace: "~/.openclaw/workspace",
    model: {
      primary: "anthropic/claude-sonnet-4-5",
      fallbacks: ["anthropic/claude-opus-4-6"]
    }
  },
  channels: {
    whatsapp: {
      allowFrom: ["+15555550123"]
    }
  }
}

Key production settings:

• Bind to loopback only — no external access without a reverse proxy
• Token auth on the gateway — prevents unauthorized API access
• Disable Control UI — reduces attack surface
• Set allowFrom on channels — only authorized senders can interact

Common Issues

"Model not found" Error

Model refs use provider/model format (split on first /):

• ✅ anthropic/claude-sonnet-4-5
• ❌ claude-sonnet
• ❌ anthropic:claude-sonnet-4-5

"Invalid API key" Error

Check that:

1. Your key starts with sk-ant-
2. The key has not been revoked
3. The environment variable is set: echo $ANTHROPIC_API_KEY
4. Or your auth profile is configured: openclaw config get auth

High Latency

If responses are slow:

• Switch from Opus to Sonnet for faster responses
• Reduce context size by limiting workspace scope
• Check your network connection to Anthropic's API

Token Limit Errors

If you hit token limits:

• Use Sonnet (200K context) for large codebases
• Consider breaking tasks into smaller steps
• Use the /model command to switch to a cheaper model for simpler tasks

Cost Management

Estimated costs (as of 2026):

Cost optimization tips:

1. Use Sonnet by default — Opus only when needed
2. Set fallbacks to cheaper models — Use Gemini Flash or GPT-5.2 as cost-efficient fallbacks
3. Cache common responses — Reduce redundant API calls
4. Monitor usage — Check Anthropic dashboard regularly

With Clawctl

If you're using Clawctl, Claude configuration is simpler. Sign up at clawctl.com/checkout, and the dashboard setup wizard walks you through it:

1. Select Anthropic as your provider
2. Paste your API key
3. Clawctl validates the connection and deploys

No config files. No environment variables. Just pick your model and go.

Clawctl handles:

• Secure credential storage (AES-256-GCM encrypted)
• Production gateway security
• Token usage monitoring
• Cost alerts

Deploy Claude + OpenClaw securely →

Full OpenClaw documentation →