openclaw-installer-deployment

Q: How do I install openclaw-installer-deployment?

Run npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-installer-deployment 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-installer-deployment/ (personal) or .claude/skills/openclaw-installer-deployment/ (project).

by reason-machinesDevOps & Cloud

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

Installs: 165
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-installer-deployment

01
Install
Run the command in your project. The CLI asks which agents to install for.
02
Describe the task
Ask your agent for something this skill covers. It loads openclaw-installer-deployment automatically when relevant.
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 Installer & Deployment

Skill by ara.so — Hermes Skills collection.

OpenClaw is a private AI assistant deployment tool supporting multiple AI models (Claude, GPT, Gemini, etc.) and messaging platforms (Telegram, Discord, WhatsApp, Slack, WeChat, iMessage, Feishu). This skill covers installation, configuration, service management, and troubleshooting.

What OpenClaw Does

Multi-Model AI: Supports Anthropic Claude, OpenAI GPT, Google Gemini, OpenRouter, Groq, Mistral AI, and Ollama
Multi-Channel: Integrates with Telegram, Discord, WhatsApp, Slack, WeChat, iMessage (macOS), and Feishu
Persistent Memory: Cross-conversation, cross-platform long-term memory
Proactive Features: Scheduled reminders, morning briefings, alerts
Custom Skills: Define capabilities via Markdown files
Remote Control: Execute system commands, file operations, web browsing

Installation

One-Line Install (Recommended)

# Automatic installation with environment detection
curl -fsSL https://raw.githubusercontent.com/miaoxworld/OpenClawInstaller/main/install.sh | bash

The installer automatically:

Detects OS and installs dependencies (Node.js v22+)
Installs OpenClaw globally via npm
Guides core configuration (AI model, identity)
Tests API connections
Auto-starts OpenClaw gateway service
Optional: Opens configuration menu for channels

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 macOS permissions issue, install OpenClaw first
npm install -g openclaw

Desktop Manager (Alternative)

For GUI-based management, use OpenClaw Manager (Tauri 2.0 + React + TypeScript + Rust):

Repository: https://github.com/miaoxworld/openclaw-manager
Features: Real-time monitoring, visual config, cross-platform (macOS/Windows/Linux)

System Requirements

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

Configuration

Directory Structure

~/.openclaw/
├── openclaw.json        # Core configuration (auto-managed)
├── env                  # Environment variables (API keys)
├── config-menu.sh       # Interactive configuration script
├── backups/             # Config backups
└── logs/                # Log files

Environment Variables (`~/.openclaw/env`)

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

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

# Google Gemini
export GEMINI_API_KEY=xxxxx

# OpenRouter
export OPENROUTER_API_KEY=sk-or-xxxxx

# Telegram
export TELEGRAM_BOT_TOKEN=123456:ABC-DEF...
export TELEGRAM_USER_ID=123456789

# Discord
export DISCORD_BOT_TOKEN=xxxxx
export DISCORD_CHANNEL_ID=123456789

# Feishu
export FEISHU_APP_ID=cli_xxxxx
export FEISHU_APP_SECRET=xxxxx

Interactive Configuration Menu

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

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

Menu options:

User Identity: Name, timezone, language preferences
AI Model: Configure provider (Anthropic, OpenAI, Gemini, etc.)
Message Channels: Telegram, Discord, WhatsApp, Feishu, etc.
Quick Tests: API connectivity, channel verification
Advanced: Backup/restore, view config, diagnostics

AI Model Configuration

Anthropic Claude (with Custom API Support)

# Using configuration menu
# 1. Select Anthropic Claude
# 2. Enter custom API URL (leave empty for official API)
# 3. Enter API key
# 4. Select model (recommended: claude-sonnet-4-5-20250929)

Environment setup:

export ANTHROPIC_API_KEY=sk-ant-xxxxx
export ANTHROPIC_BASE_URL=https://your-oneapi-proxy.com  # Optional

Config file (~/.openclaw/openclaw.json):

{
  "models": {
    "providers": {
      "anthropic-custom": {
        "baseUrl": "https://your-oneapi-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
          }
        ]
      }
    }
  }
}

OpenAI GPT (with Custom API Support)

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

# Environment variables
export OPENAI_API_KEY=sk-xxxxx
export OPENAI_BASE_URL=https://your-api-proxy.com/v1

Ollama (Local Deployment)

# Install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# Pull a model
ollama pull llama3

# Configure in menu: select Ollama, enter model name (llama3)

Channel Configuration

Telegram Bot

# 1. Create bot with @BotFather on Telegram
# 2. Send /newbot and follow prompts
# 3. Copy Bot Token
# 4. Get User ID from @userinfobot
# 5. Configure via menu or set env vars:

export TELEGRAM_BOT_TOKEN=123456:ABC-DEF...
export TELEGRAM_USER_ID=123456789

Discord Bot

# 1. Create app at https://discord.com/developers/applications
# 2. Go to Bot → Reset Token (copy token)
# 3. Enable "Message Content Intent" (critical!)
# 4. Invite bot: OAuth2 → URL Generator
#    - Scopes: bot
#    - Permissions: View Channels, Send Messages, Read Message History
# 5. Get Channel ID: Enable Developer Mode → Right-click channel → Copy ID

export DISCORD_BOT_TOKEN=xxxxx
export DISCORD_CHANNEL_ID=123456789

Feishu (Lark) Bot

# 1. Create app at https://open.feishu.cn/
# 2. Add "Bot" capability
# 3. Add permissions: im:message, im:message:send_as_bot, im:chat:readonly
# 4. Publish app
# 5. Configure event subscription:
#    - Use "Long Connection" (WebSocket)
#    - Add event: im.message.receive_v1
#    - No webhook URL needed
# 6. Add bot to group chat

export FEISHU_APP_ID=cli_xxxxx
export FEISHU_APP_SECRET=xxxxx

Full guide: docs/feishu-setup.md

WhatsApp (QR Code Login)

# 1. Select WhatsApp in config menu
# 2. Scan QR code in terminal
# 3. Login succeeds, restart gateway
# Note: Only one WhatsApp Web session allowed

Service Management

Core Commands

# Start gateway (background daemon)
openclaw gateway start

# Stop gateway
openclaw gateway stop

# Restart gateway
openclaw gateway restart

# Check status
openclaw gateway status

# Run in foreground (debug mode)
source ~/.openclaw/env && openclaw gateway

# View logs
openclaw logs

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

Configuration Commands

# Open config file
openclaw config

# Run onboarding wizard
openclaw onboard

# Diagnose configuration issues
openclaw doctor

# Health check
openclaw health

Data Management

# Export conversation history
openclaw export --format json

# Clear memory
openclaw memory clear

# Backup data
openclaw backup

Common Patterns

Post-Install Startup

# After installation, load environment and start service
source ~/.openclaw/env
openclaw gateway start

# Verify it's running
openclaw gateway status

Adding a New AI Model

# Run config menu
bash ~/.openclaw/config-menu.sh

# Select: [2] AI Model Configuration
# Choose provider (e.g., Anthropic Claude)
# Enter custom API URL if using proxy (or leave empty)
# Enter API key
# Select model from list
# Restart gateway

openclaw gateway restart

Adding a New Channel

# Run config menu
bash ~/.openclaw/config-menu.sh

# Select: [3] Message Channel Configuration
# Choose channel (e.g., Telegram)
# Enter required credentials (token, user ID)
# Restart gateway

openclaw gateway restart

Testing API Connection

# Using config menu
bash ~/.openclaw/config-menu.sh
# Select: [4] Quick Tests → [1] Test API Connection

# Or manually check health
openclaw health

Switching AI Models

# Edit environment variables
nano ~/.openclaw/env

# Change API key and base URL
export ANTHROPIC_API_KEY=new-key
export ANTHROPIC_BASE_URL=https://new-proxy.com

# Update model in config (or use menu)
openclaw models set anthropic-custom claude-sonnet-4-5-20250929

# Restart
openclaw gateway restart

Troubleshooting

Installation Issues

# Check Node.js version (must be v22+)
node --version

# If Node.js version is old, install via nvm
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
source ~/.bashrc  # or ~/.zshrc
nvm install 22
nvm use 22

# Reinstall OpenClaw
npm install -g openclaw

Gateway Won't Start

# Check if service is already running
openclaw gateway status

# Stop existing service
openclaw gateway stop

# Check for port conflicts (default: 3000)
lsof -i :3000
# Kill conflicting process if needed
kill -9 <PID>

# Run diagnostics
openclaw doctor

# Start in foreground to see errors
source ~/.openclaw/env
openclaw gateway

API Connection Failures

# Verify environment variables are loaded
source ~/.openclaw/env
env | grep ANTHROPIC  # or OPENAI, GEMINI, etc.

# Test API manually with curl
curl -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":1024,"messages":[{"role":"user","content":"Hi"}]}' \
     ${ANTHROPIC_BASE_URL:-https://api.anthropic.com}/v1/messages

# Check OpenClaw diagnostics
openclaw doctor

Channel Not Responding

# Telegram: Verify bot token and user ID
curl https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/getMe

# Discord: Check Message Content Intent is enabled
# (Must be set in Discord Developer Portal)

# Feishu: Ensure long connection event subscription is configured
# and OpenClaw gateway is running before saving Feishu config

# View logs for errors
openclaw logs --follow

WhatsApp QR Code Not Showing

# Ensure terminal supports Unicode
# Try a different terminal emulator

# Check if WhatsApp is already logged in elsewhere
# (Only one Web session allowed)

# Restart gateway and try again
openclaw gateway restart

Custom API Proxy Issues

# Anthropic: Ensure base URL doesn't include /v1
# Correct:   https://api.example.com
# Incorrect: https://api.example.com/v1

# OpenAI: Must support v1/responses endpoint, not just v1/chat/completions
# Test with:
curl -H "Authorization: Bearer $OPENAI_API_KEY" \
     ${OPENAI_BASE_URL}/responses

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

Configuration Reset

# Backup current config
openclaw backup

# Remove config files
rm -rf ~/.openclaw/openclaw.json ~/.openclaw/env

# Re-run installer or onboarding
openclaw onboard

# Or use interactive menu
curl -fsSL https://raw.githubusercontent.com/miaoxworld/OpenClawInstaller/main/config-menu.sh | bash

Memory/Performance Issues

# Check memory usage
openclaw health

# Clear old memories
openclaw memory clear

# Restart gateway
openclaw gateway restart

# For macOS: Increase Node.js memory limit
export NODE_OPTIONS="--max-old-space-size=4096"
openclaw gateway start

Real-World Examples

Complete Setup Flow

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

# 2. Configure Anthropic Claude with custom API
bash ~/.openclaw/config-menu.sh
# → [2] AI Model Configuration
# → [1] Anthropic Claude
# → Enter custom API: https://my-oneapi.com
# → Enter API key: sk-ant-xxxxx
# → Select model: claude-sonnet-4-5-20250929

# 3. Configure Telegram
# (Get token from @BotFather, user ID from @userinfobot)
# → [3] Message Channel Configuration
# → [1] Telegram Bot
# → Enter bot token: 123456:ABC-DEF...
# → Enter user ID: 123456789

# 4. Start service
openclaw gateway start

# 5. Test by messaging your Telegram bot

Multi-Channel Setup

# Configure multiple channels for the same AI backend
source ~/.openclaw/env

# Set up Telegram
export TELEGRAM_BOT_TOKEN=xxxxx
export TELEGRAM_USER_ID=xxxxx

# Set up Discord
export DISCORD_BOT_TOKEN=xxxxx
export DISCORD_CHANNEL_ID=xxxxx

# Set up Feishu
export FEISHU_APP_ID=cli_xxxxx
export FEISHU_APP_SECRET=xxxxx

# Restart to apply all channels
openclaw gateway restart

# Now OpenClaw responds on all platforms with shared memory

Custom Skills Definition

OpenClaw supports custom skills via Markdown files. Example structure:

# Custom Skill: Weather Check

Trigger phrases:
- "what's the weather"
- "check weather"

Actions:
1. Call weather API
2. Format response
3. Send to user

Skills are typically stored in ~/.openclaw/skills/ (check OpenClaw documentation for exact format).

Key Takeaways

Use the installer script for automatic environment setup
Configure via menu (config-menu.sh) for interactive guided setup
Load environment (source ~/.openclaw/env) before manual commands
Custom APIs: Anthropic/OpenAI support custom base URLs (OneAPI, NewAPI, etc.)
OpenAI proxies: Must support v1/responses endpoint (Responses API)
Feishu: Use long connection mode (no webhook needed)
WhatsApp: Only one Web session allowed per account
Service management: Use openclaw gateway start/stop/restart/status
Troubleshooting: Run openclaw doctor for diagnostics
Multi-channel: All channels share the same AI backend and memory

For latest updates and issues: https://github.com/miaoxworld/OpenClawInstaller

FAQ

What does the openclaw-installer-deployment skill do?

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

How do I install openclaw-installer-deployment?

Run npx skills add https://github.com/reason-machines/hermes-skills --skill openclaw-installer-deployment 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-installer-deployment/ (personal) or .claude/skills/openclaw-installer-deployment/ (project).

Which AI agents can use openclaw-installer-deployment?

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-installer-deployment 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-installer-deployment?

It is published by reason-machines in reason-machines/hermes-skills. It has 165 recorded 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

openclaw-installer-deployment

Install

Install

Describe the task

Review the result

SKILL.md

OpenClaw Installer & Deployment

What OpenClaw Does

Installation

One-Line Install (Recommended)

Manual Installation

Desktop Manager (Alternative)

System Requirements

Configuration

Directory Structure

Environment Variables (~/.openclaw/env)

Interactive Configuration Menu

AI Model Configuration

Anthropic Claude (with Custom API Support)

OpenAI GPT (with Custom API Support)

Ollama (Local Deployment)

Channel Configuration

Telegram Bot

Discord Bot

Feishu (Lark) Bot

WhatsApp (QR Code Login)

Service Management

Core Commands

Configuration Commands

Data Management

Common Patterns

Post-Install Startup

Adding a New AI Model

Adding a New Channel

Testing API Connection

Switching AI Models

Troubleshooting

Installation Issues

Gateway Won't Start

API Connection Failures

Channel Not Responding

WhatsApp QR Code Not Showing

Custom API Proxy Issues

Configuration Reset

Memory/Performance Issues

Real-World Examples

Complete Setup Flow

Multi-Channel Setup

Custom Skills Definition

Key Takeaways

FAQ

More from reason-machines/hermes-skills

Popular devops & cloud skills

Environment Variables (`~/.openclaw/env`)