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 20+ — Required for OpenClaw

Step 1: Configure Your API Key

Add your Anthropic API key to the OpenClaw configuration:

Option A: Environment variable (recommended for production)

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

Option B: Configuration file

In your openclaw.json:

{
  "credentials": {
    "anthropic": {
      "apiKey": "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 the Claude model in your agent settings:

{
  "agents": {
    "list": [
      {
        "id": "main",
        "model": "anthropic/claude-sonnet-4-5",
        "workspace": "/path/to/your/workspace"
      }
    ]
  }
}

Model options:

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

Step 3: Configure System Prompt

Set your agent's behavior and personality:

{
  "agents": {
    "list": [
      {
        "id": "main",
        "model": "anthropic/claude-sonnet-4-5",
        "systemPrompt": "You are a helpful AI assistant for software development. You have access to the filesystem and can run shell commands. Be concise and technical. Ask clarifying questions when requirements are ambiguous."
      }
    ]
  }
}

Tips for effective system prompts:

• Be specific about the agent's role
• Define boundaries (what it should/shouldn't do)
• Set tone and communication style
• Include relevant context about your domain

Step 4: Enable Tools

Configure which tools your agent can use:

{
  "agents": {
    "list": [
      {
        "id": "main",
        "model": "anthropic/claude-sonnet-4-5",
        "tools": {
          "filesystem": {
            "enabled": true,
            "allowedPaths": ["/home/user/projects"]
          },
          "shell": {
            "enabled": true,
            "allowedCommands": ["git", "npm", "node", "python"]
          },
          "browser": {
            "enabled": false
          }
        }
      }
    ]
  }
}

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

Step 5: Set Token Limits

Prevent runaway costs with token limits:

{
  "agents": {
    "list": [
      {
        "id": "main",
        "model": "anthropic/claude-sonnet-4-5",
        "tokenLimits": {
          "maxInputTokens": 100000,
          "maxOutputTokens": 4096,
          "maxTokensPerDay": 1000000
        }
      }
    ]
  }
}

Considerations:

• Higher limits allow more complex tasks
• Lower limits control costs
• Daily limits prevent billing surprises

Step 6: Test Locally

Start OpenClaw and verify the setup:

openclaw start

Test with a simple prompt:

openclaw chat "What model are you running?"

Expected response should confirm Claude Sonnet.

Test tool access:

openclaw chat "List the files in the current directory"

Verify the agent can use the filesystem tool.

Step 7: Production Configuration

For production deployment, add security settings:

{
  "gateway": {
    "host": "127.0.0.1",
    "port": 3000,
    "authToken": "your-secure-token",
    "controlUI": false,
    "mdns": false
  },
  "agents": {
    "list": [
      {
        "id": "main",
        "model": "anthropic/claude-sonnet-4-5",
        "workspace": "/app/workspace"
      }
    ]
  },
  "security": {
    "promptDefense": true,
    "egressControl": {
      "enabled": true,
      "allowedDomains": [
        "api.anthropic.com",
        "api.github.com"
      ]
    }
  }
}

Common Issues

"Model not found" Error

Verify your model string is correct:

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

"Invalid API key" Error

Check that:

1. The key starts with sk-ant-
2. The key has not been revoked
3. The environment variable is set correctly

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:

• Increase maxOutputTokens for longer responses
• Use Sonnet (200K context) for large codebases
• Consider breaking tasks into smaller steps

Cost Management

Estimated costs (as of 2026):

Cost optimization tips:

1. Use Sonnet by default — Opus only when needed
2. Set daily token limits — Prevent billing surprises
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
• Production security settings
• Token usage monitoring
• Cost alerts

Deploy Claude + OpenClaw securely →

Full OpenClaw documentation →