MCPInstall

openclaw-deployment-installer

Deploy and configure OpenClaw AI assistant with multi-model support and messaging channel integrations

Installs
162
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-deployment-installer
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads openclaw-deployment-installer automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

OpenClaw Deployment & Installer

Skill by ara.so — Hermes Skills collection.

OpenClawInstaller is a one-click deployment tool for OpenClaw (aka ClawdBot), a private AI assistant with persistent memory, proactive messaging, and multi-channel support. It supports Anthropic Claude, OpenAI GPT, Google Gemini, and local models via Ollama. Messaging integrations include Telegram, Discord, WhatsApp, Slack, WeChat, iMessage (macOS), and Feishu.

Installation

One-Click Install (Recommended)

curl -fsSL https://raw.githubusercontent.com/miaoxworld/OpenClawInstaller/main/install.sh | bash

This script:

  1. Detects system environment and installs dependencies
  2. Installs Node.js v22+ (if needed)
  3. Installs OpenClaw via npm
  4. Runs onboarding wizard for AI model and identity configuration
  5. Tests API connectivity
  6. Auto-starts the OpenClaw Gateway service
  7. Optionally opens configuration menu for channel setup

Manual Installation

# Clone repository
git clone https://github.com/miaoxworld/OpenClawInstaller.git
cd OpenClawInstaller

# Add execute permissions
chmod +x install.sh config-menu.sh

# Run installer
./install.sh

# If permission issues on macOS, install OpenClaw first
npm install -g openclaw

Desktop Manager (GUI Alternative)

For graphical interface, use OpenClaw Manager (Tauri 2.0 + React + Rust):

System Requirements

  • OS: macOS 12+, Ubuntu 20.04+, Debian 11+, CentOS 8+
  • Node.js: v22 or higher
  • Memory: 2GB minimum, 4GB+ recommended
  • Disk: 1GB minimum

Core Commands

Service Management

# Start service (background daemon)
openclaw gateway start

# Stop service
openclaw gateway stop

# Restart service
openclaw gateway restart

# Check service status
openclaw gateway status

# Run in foreground (debugging)
openclaw gateway

# View logs
openclaw logs

# Follow logs in real-time
openclaw logs --follow

Configuration Management

# Open configuration file
openclaw config

# Run onboarding wizard
openclaw onboard

# Diagnose configuration issues
openclaw doctor

# Health check
openclaw health

# Set configuration values
openclaw config set <key> <value>

# Set model
openclaw models set <provider> <model>

Data Management

# Export conversation history
openclaw export --format json

# Clear memory
openclaw memory clear

# Backup data
openclaw backup

Configuration Menu (Interactive)

# Run configuration menu from installation directory
bash ~/.openclaw/config-menu.sh

# Or download and run directly
curl -fsSL https://raw.githubusercontent.com/miaoxworld/OpenClawInstaller/main/config-menu.sh | bash

AI Model Configuration

Supported Providers

  • Anthropic Claude: claude-sonnet-4-5, claude-opus-4-5, claude-haiku-4-5 (supports custom API base URL)
  • OpenAI GPT: gpt-4o, gpt-4o-mini, gpt-4-turbo (supports custom API base URL with v1/responses support)
  • Google Gemini: gemini-2.0-flash, gemini-1.5-pro, gemini-1.5-flash
  • OpenRouter: Multi-model gateway (claude-sonnet-4, gpt-4o, gemini-pro-1.5)
  • Groq: llama-3.3-70b-versatile, llama-3.1-8b-instant, mixtral-8x7b
  • Mistral AI: mistral-large-latest, mistral-small-latest, codestral-latest
  • Ollama: Local deployment (llama3, mistral, etc.)

Anthropic Claude Setup

# Environment variables (stored in ~/.openclaw/env)
export ANTHROPIC_API_KEY="your-api-key-here"
export ANTHROPIC_BASE_URL="https://custom-api-endpoint.com"  # Optional

# Configure via CLI
openclaw models set anthropic claude-sonnet-4-5-20250929

OpenAI GPT Setup

⚠️ Important: Custom OpenAI API endpoints must support Responses API (v1/responses), not just Chat Completions (v1/chat/completions).

# Environment variables
export OPENAI_API_KEY="your-api-key-here"
export OPENAI_BASE_URL="https://custom-api-endpoint.com/v1"  # Optional

# Configure via CLI
openclaw models set openai gpt-4o

Custom Provider Configuration

For custom API endpoints (e.g., OneAPI, NewAPI), the installer creates a custom provider in ~/.openclaw/openclaw.json:

{
  "models": {
    "providers": {
      "anthropic-custom": {
        "baseUrl": "https://your-api-proxy.com",
        "apiKey": "${ANTHROPIC_API_KEY}",
        "models": [
          {
            "id": "claude-sonnet-4-5-20250929",
            "name": "claude-sonnet-4-5-20250929",
            "api": "anthropic-messages",
            "input": ["text"],
            "contextWindow": 200000,
            "maxTokens": 8192
          }
        ]
      }
    }
  }
}

Ollama (Local Model) Setup

# Install Ollama first: https://ollama.ai
ollama pull llama3

# Configure OpenClaw
openclaw models set ollama llama3

Messaging Channel Configuration

Telegram Bot

  1. Create bot with BotFather:
# In Telegram, message @BotFather
/newbot
# Follow prompts, get Bot Token
  1. Get your User ID:
# Message @userinfobot
# Copy your User ID
  1. Configure via menu or manually edit ~/.openclaw/openclaw.json:
{
  "telegram": {
    "token": "123456789:ABCdefGHIjklMNOpqrsTUVwxyz",
    "userId": "987654321"
  }
}

Discord Bot

  1. Create application at Discord Developer Portal
  2. Go to Bot section → Reset Token → Copy token
  3. Enable "Message Content Intent" (critical!)
  4. Invite bot via OAuth2 URL Generator (scopes: bot, permissions: View Channels, Send Messages, Read Message History)
  5. Get Channel ID: Enable Developer Mode → Right-click channel → Copy Channel ID

Configure:

{
  "discord": {
    "token": "your-bot-token",
    "channelId": "1234567890123456789"
  }
}

Feishu (Lark) Bot

No public server required — uses WebSocket long-connection mode.

  1. Create app at Feishu Open Platform
  2. Add "Bot" capability
  3. Get App ID and App Secret
  4. Add permissions: im:message, im:message:send_as_bot, im:chat:readonly
  5. Publish app
  6. Configure event subscription:
    • Use long-connection mode (no webhook URL needed)
    • Add event: im.message.receive_v1
    • ⚠️ OpenClaw service must be running to save settings

Configure:

{
  "feishu": {
    "appId": "cli_xxxxxxxxx",
    "appSecret": "your-app-secret"
  }
}

WhatsApp

No Business API needed — uses personal account via QR code.

# Run configuration menu → WhatsApp option
# Scan QR code displayed in terminal
# Restart gateway after login
openclaw gateway restart

⚠️ Note: WhatsApp Web can only be active on one device. Configuring here will log out existing WhatsApp Web sessions.

Configuration Files

Directory Structure

~/.openclaw/
├── openclaw.json        # Core configuration (models, channels, skills)
├── env                  # Environment variables (API keys, base URLs)
├── backups/             # Configuration backups
└── logs/                # Log files (managed by OpenClaw)

Environment Variables (~/.openclaw/env)

# Anthropic Claude
export ANTHROPIC_API_KEY="sk-ant-xxxxx"
export ANTHROPIC_BASE_URL="https://custom-endpoint.com"  # Optional

# OpenAI GPT
export OPENAI_API_KEY="sk-xxxxx"
export OPENAI_BASE_URL="https://custom-endpoint.com/v1"  # Optional

# Google Gemini
export GEMINI_API_KEY="your-gemini-key"

# OpenRouter
export OPENROUTER_API_KEY="sk-or-xxxxx"

# Groq
export GROQ_API_KEY="gsk_xxxxx"

# Mistral AI
export MISTRAL_API_KEY="your-mistral-key"

Core Configuration (~/.openclaw/openclaw.json)

{
  "models": {
    "default": "claude-sonnet-4-5-20250929",
    "providers": {
      "anthropic": {
        "apiKey": "${ANTHROPIC_API_KEY}",
        "models": ["claude-sonnet-4-5-20250929"]
      }
    }
  },
  "telegram": {
    "token": "${TELEGRAM_BOT_TOKEN}",
    "userId": "123456789"
  },
  "discord": {
    "token": "${DISCORD_BOT_TOKEN}",
    "channelId": "987654321"
  },
  "memory": {
    "enabled": true,
    "maxMessages": 1000
  },
  "skills": {
    "enabled": true,
    "directory": "~/.openclaw/skills"
  }
}

Common Patterns

Testing API Connection

# After configuring AI model
openclaw doctor

# Test specific model
openclaw models test anthropic claude-sonnet-4-5-20250929

Adding Custom Skills

# Skills are Markdown files in ~/.openclaw/skills/
mkdir -p ~/.openclaw/skills

cat > ~/.openclaw/skills/weather.md << 'EOF'
# Weather Information

You can fetch weather information for any city.

## Usage
When user asks about weather:
1. Extract city name
2. Use curl to fetch from weather API
3. Format and present results
EOF

# Restart gateway to load skills
openclaw gateway restart

Monitoring Service Status

# Check if gateway is running
openclaw gateway status

# View recent logs
openclaw logs --tail 50

# Watch logs in real-time
openclaw logs --follow

# Health check with detailed output
openclaw health --verbose

Switching AI Models

# Change to different model
openclaw models set anthropic claude-opus-4-5

# Change to different provider
openclaw models set openai gpt-4o

# Verify current model
openclaw config get models.default

Backup and Restore

# Backup all configuration and data
openclaw backup --output ~/openclaw-backup-$(date +%Y%m%d).tar.gz

# Restore from backup
openclaw restore ~/openclaw-backup-20260517.tar.gz

# Export conversations only
openclaw export --format json --output ~/conversations.json

Troubleshooting

Service Won't Start

# Check for errors
openclaw doctor

# View detailed logs
openclaw logs --level debug

# Verify Node.js version
node --version  # Should be v22+

# Check environment variables
source ~/.openclaw/env
echo $ANTHROPIC_API_KEY

API Key Not Working

# Test API key manually
curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-sonnet-4-5-20250929","max_tokens":10,"messages":[{"role":"user","content":"Hi"}]}'

# For custom base URL
curl https://your-custom-endpoint.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-sonnet-4-5-20250929","max_tokens":10,"messages":[{"role":"user","content":"Hi"}]}'

Telegram Bot Not Responding

# Verify bot token and user ID
cat ~/.openclaw/openclaw.json | grep -A 3 telegram

# Check logs for errors
openclaw logs | grep telegram

# Test bot manually
curl https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getMe

Discord Bot Not Responding

  1. Verify Message Content Intent is enabled in Discord Developer Portal
  2. Check bot has permissions in target channel
  3. Verify channel ID is correct:
# Check configuration
openclaw config get discord.channelId

# View logs
openclaw logs | grep discord

Feishu Bot Not Receiving Messages

  1. Ensure OpenClaw gateway is running when saving event subscription settings
  2. Verify long-connection mode is selected (not webhook)
  3. Check permissions are granted and app is published
  4. View logs:
openclaw logs | grep feishu

WhatsApp Connection Lost

# Re-authenticate by reconfiguring
bash ~/.openclaw/config-menu.sh
# Select WhatsApp → Scan new QR code

# Restart gateway
openclaw gateway restart

Memory/Performance Issues

# Clear old memory
openclaw memory clear --before 2026-01-01

# Reduce context window in config
openclaw config set memory.maxMessages 500

# Monitor resource usage
openclaw health --verbose

Custom API Endpoint Not Working

For Anthropic:

# Verify baseUrl format (no /v1 suffix)
echo $ANTHROPIC_BASE_URL  # Should be: https://api.example.com

# Test endpoint
curl $ANTHROPIC_BASE_URL/v1/messages -H "x-api-key: $ANTHROPIC_API_KEY" -H "anthropic-version: 2023-06-01" -d '{"model":"claude-sonnet-4-5-20250929","max_tokens":10,"messages":[{"role":"user","content":"test"}]}'

For OpenAI (must support v1/responses):

# Verify endpoint supports Responses API
curl $OPENAI_BASE_URL/responses \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","input":[{"role":"user","content":"test"}],"max_tokens":10}'

# If 404, your endpoint doesn't support Responses API

Clean Reinstall

# Stop service
openclaw gateway stop

# Backup data
openclaw backup

# Uninstall
npm uninstall -g openclaw
rm -rf ~/.openclaw

# Reinstall
curl -fsSL https://raw.githubusercontent.com/miaoxworld/OpenClawInstaller/main/install.sh | bash

Advanced Configuration

Multiple AI Models (Fallback)

Edit ~/.openclaw/openclaw.json:

{
  "models": {
    "default": "claude-sonnet-4-5-20250929",
    "fallback": ["gpt-4o", "gemini-2.0-flash"],
    "providers": {
      "anthropic": { "apiKey": "${ANTHROPIC_API_KEY}" },
      "openai": { "apiKey": "${OPENAI_API_KEY}" },
      "google": { "apiKey": "${GEMINI_API_KEY}" }
    }
  }
}

Scheduled Proactive Messages

# Create skill for morning briefing
cat > ~/.openclaw/skills/morning-briefing.md << 'EOF'
# Morning Briefing

Every day at 8 AM, send a summary of:
- Today's calendar events
- Weather forecast
- Important reminders

## Schedule
- Time: 08:00
- Timezone: UTC
EOF

openclaw gateway restart

Custom System Prompt

Edit ~/.openclaw/openclaw.json:

{
  "system": {
    "prompt": "You are a helpful AI assistant named OpenClaw. You have persistent memory across conversations and can proactively send messages. Be concise and friendly."
  }
}

This skill covers the essential deployment, configuration, service management, and troubleshooting workflows for OpenClaw using the installer tools.

FAQ

What does the openclaw-deployment-installer skill do?

Deploy and configure OpenClaw AI assistant with multi-model support and messaging channel integrations

How do I install openclaw-deployment-installer?

Run npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-deployment-installer in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/openclaw-deployment-installer/ (personal) or .claude/skills/openclaw-deployment-installer/ (project).

Which AI agents can use openclaw-deployment-installer?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is openclaw-deployment-installer safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains openclaw-deployment-installer?

It is published by reason-machines in reason-machines/hermes-skills. It has 162 recorded installs.

More from reason-machines/hermes-skills

View all →

hermes-agent-self-evolution

reason-machines/hermes-skills

Evolutionary self-improvement for Hermes Agent using DSPy + GEPA to optimize skills, prompts, and code

AI & Agents323 installs

hermes-webui-agent

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

262 installs

awesome-hermes-agent-ecosystem

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

232 installs

hermes-agent-framework

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

219 installs

hermes-workspace-ai-agent-ui

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

Frontend & Design213 installs

hermes-desktop-companion

reason-machines/hermes-skills

Open the skill to read its SKILL.md instructions.

206 installs

Popular devops & cloud skills

View category →

microsoft-foundry

microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure

OfficialDevOps & Cloud579.1K installs

azure-diagnostics

microsoft/azure-skills

Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function telemetry missing or stopped after a config/connection-string change, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, lock renewal during long-running processing, service bus dead letter.

OfficialDevOps & Cloud569.8K installs

azure-prepare

microsoft/azure-skills

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.

OfficialDevOps & Cloud569K installs

azure-ai

microsoft/azure-skills

Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.

OfficialDevOps & Cloud568.8K installs

azure-deploy

microsoft/azure-skills

Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.

OfficialDevOps & Cloud568.6K installs

azure-validate

microsoft/azure-skills

Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate Bicep, test before deploying, troubleshoot deployment errors, validate Azure Functions, validate function app, validate serverless deployment, verify RBAC roles, check role assignments, review managed identity permissions, what-if analysis, validate Container Apps deployment.

OfficialDevOps & Cloud568K installs