MCPInstall

openclaw-chinese-ai-assistant

by reason-machinesData & Databases

OpenClaw Chinese localized AI assistant platform with CLI, dashboard, multi-platform chat integration (WhatsApp/Telegram/Discord), and LLM provider support

Installs
173
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-chinese-ai-assistant
  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-chinese-ai-assistant 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 Chinese AI Assistant Skill

Skill by ara.so — Hermes Skills collection.

Overview

OpenClaw Chinese Translation is a fully localized (Simplified Chinese) distribution of OpenClaw, an open-source personal AI assistant platform with 195,000+ GitHub stars. It runs locally on your machine and provides AI assistance through popular chat platforms (WhatsApp, Telegram, Discord) with both CLI and web dashboard interfaces fully translated to Chinese.

Key Features:

  • Automatic hourly sync with upstream OpenClaw (< 1 hour delay)
  • Full Chinese localization for CLI and Dashboard
  • Multi-platform support: WhatsApp, Telegram, Discord
  • Multiple LLM providers: Claude, OpenAI, compatible APIs
  • Tool calling and skill extensions
  • Daemon/service mode for background operation
  • Web-based management dashboard

Installation

Prerequisites

Node.js >= 22 is required. Check version:

node -v

If needed, download from https://nodejs.org/

Install OpenClaw Chinese

npm install -g @qingchencloud/openclaw-zh@latest

Verify Installation

openclaw --version

Initialization and Configuration

Initial Setup with Daemon

openclaw onboard --install-daemon

This interactive wizard will guide you through:

  1. Selecting an LLM provider (Claude, OpenAI, or compatible)
  2. Configuring API credentials
  3. Setting up chat channels (WhatsApp/Telegram/Discord)
  4. Installing gateway as daemon service

Manual Configuration

View current config:

openclaw config

Edit config file directly (located at ~/.openclaw/config.yml):

llm:
  provider: openai
  api_key: ${OPENAI_API_KEY}
  model: gpt-4
  base_url: https://api.openai.com/v1  # For compatible providers

gateway:
  port: 3000
  host: 0.0.0.0

channels:
  - type: telegram
    token: ${TELEGRAM_BOT_TOKEN}
  - type: discord
    token: ${DISCORD_BOT_TOKEN}

Configure LLM Provider

For OpenAI-compatible providers (like the free gpt.qt.cool):

openclaw config set llm.provider openai-compatible
openclaw config set llm.base_url https://gpt.qt.cool/v1
openclaw config set llm.api_key ${YOUR_API_KEY}
openclaw config set llm.model gpt-4

For Claude:

openclaw config set llm.provider anthropic
openclaw config set llm.api_key ${ANTHROPIC_API_KEY}
openclaw config set llm.model claude-3-5-sonnet-20241022

Core Commands

Gateway Management

# Start gateway (foreground, for debugging)
openclaw gateway run

# Start as daemon (background, recommended)
openclaw gateway start

# Stop daemon
openclaw gateway stop

# Restart gateway
openclaw gateway restart

# Check status
openclaw gateway status

# Install as system service (auto-start on boot)
openclaw gateway install

# Uninstall system service
openclaw gateway uninstall

Dashboard

# Open web dashboard (auto-opens browser)
openclaw dashboard

# Open on specific port
openclaw dashboard --port 8080

# Access remotely with token
openclaw dashboard --host 0.0.0.0 --token ${DASHBOARD_TOKEN}

Dashboard URL: http://localhost:3000 (default)

Language Setting: After opening dashboard, go to Overview page → scroll to bottom → set Language to 简体中文 (Simplified Chinese) → refresh.

Skills Management

# List available skills
openclaw skills list

# Install a skill
openclaw skills install 1password

# Remove a skill
openclaw skills remove 1password

# Update all skills
openclaw skills update

Maintenance

# Update OpenClaw CLI
openclaw update

# Diagnose issues (auto-fix)
openclaw doctor

# View logs
openclaw logs

# Clear cache
openclaw cache clear

Real-World Usage Examples

Example 1: Deploy with Custom LLM Provider

#!/bin/bash

# Set environment variables
export OPENAI_API_KEY="sk-your-key-here"
export TELEGRAM_BOT_TOKEN="123456:ABC-DEF-your-token"

# Install
npm install -g @qingchencloud/openclaw-zh@latest

# Configure programmatically
openclaw config set llm.provider openai-compatible
openclaw config set llm.base_url https://gpt.qt.cool/v1
openclaw config set llm.api_key "${OPENAI_API_KEY}"
openclaw config set llm.model gpt-4

# Add Telegram channel
openclaw config set channels.0.type telegram
openclaw config set channels.0.token "${TELEGRAM_BOT_TOKEN}"

# Start daemon
openclaw gateway start

# Verify running
openclaw gateway status

Example 2: Docker Deployment

Create docker-compose.yml:

version: '3.8'

services:
  openclaw:
    image: ghcr.io/1186258278/openclaw-chinese:latest
    container_name: openclaw-zh
    restart: unless-stopped
    ports:
      - "3000:3000"
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY}
      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
      - TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN}
      - DASHBOARD_TOKEN=${DASHBOARD_TOKEN}
    volumes:
      - ./data:/root/.openclaw
      - ./logs:/var/log/openclaw

Run:

docker-compose up -d

Example 3: Remote Access with Nginx

Nginx config for HTTPS dashboard access:

server {
    listen 443 ssl;
    server_name openclaw.example.com;

    ssl_certificate /path/to/cert.pem;
    ssl_certificate_key /path/to/key.pem;

    location / {
        proxy_pass http://127.0.0.1:3000;
        proxy_http_version 1.1;
        proxy_set_header Upgrade $http_upgrade;
        proxy_set_header Connection 'upgrade';
        proxy_set_header Host $host;
        proxy_cache_bypass $http_upgrade;
        
        # WebSocket support
        proxy_set_header X-Real-IP $remote_addr;
        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
        proxy_set_header X-Forwarded-Proto $scheme;
    }
}

Example 4: Programmatic Agent Creation (JavaScript)

// Create custom agent configuration
const fs = require('fs');
const path = require('path');
const yaml = require('js-yaml');

const configPath = path.join(process.env.HOME, '.openclaw', 'config.yml');
const config = yaml.load(fs.readFileSync(configPath, 'utf8'));

// Add new agent
config.agents = config.agents || [];
config.agents.push({
  name: 'research-assistant',
  model: 'gpt-4',
  system_prompt: '你是一个专业的研究助手，帮助用户查找和总结信息。',
  skills: ['web-search', 'summarize', 'markdown'],
  max_tokens: 4000,
  temperature: 0.7
});

// Save config
fs.writeFileSync(configPath, yaml.dump(config), 'utf8');
console.log('Agent created successfully');

Example 5: Monitoring Gateway Status

#!/bin/bash

# Check if gateway is running
if openclaw gateway status | grep -q "running"; then
    echo "Gateway is healthy"
    exit 0
else
    echo "Gateway is down, restarting..."
    openclaw gateway restart
    sleep 5
    if openclaw gateway status | grep -q "running"; then
        echo "Gateway restarted successfully"
        exit 0
    else
        echo "Failed to restart gateway"
        exit 1
    fi
fi

Common Patterns

Pattern 1: Multi-Model Setup

Configure different models for different tasks:

agents:
  - name: fast-assistant
    model: gpt-3.5-turbo
    use_case: quick_questions
  
  - name: deep-thinker
    model: claude-3-opus-20240229
    use_case: complex_reasoning
  
  - name: code-helper
    model: gpt-4
    skills: ['code-interpreter', 'github']

Pattern 2: Environment-Based Config

Use environment variables for secrets:

# .env file
OPENAI_API_KEY=sk-proj-...
ANTHROPIC_API_KEY=sk-ant-...
TELEGRAM_BOT_TOKEN=123456:ABC...
WHATSAPP_PHONE_NUMBER=+1234567890
DASHBOARD_TOKEN=secure-random-token-here

# Load in config.yml
llm:
  api_key: ${OPENAI_API_KEY}

channels:
  - type: telegram
    token: ${TELEGRAM_BOT_TOKEN}
  - type: whatsapp
    phone: ${WHATSAPP_PHONE_NUMBER}

Pattern 3: Skill Chains

Combine multiple skills for complex workflows:

// Example: Research and summarize workflow
const workflow = {
  steps: [
    { skill: 'web-search', query: '${user_query}' },
    { skill: 'summarize', input: '${search_results}' },
    { skill: 'markdown', format: 'report', input: '${summary}' }
  ]
};

Troubleshooting

Gateway Won't Start

# Check if port 3000 is already in use
lsof -i :3000  # macOS/Linux
netstat -ano | findstr :3000  # Windows

# Run diagnostics
openclaw doctor

# Check logs
openclaw logs --tail 100

# Try alternative port
openclaw gateway run --port 3001

Dashboard Connection Issues

  1. Cannot access dashboard remotely:
# Start with external access
openclaw dashboard --host 0.0.0.0 --token your-secure-token

# Or edit config
openclaw config set gateway.host 0.0.0.0
openclaw config set gateway.dashboard_token your-secure-token
openclaw gateway restart
  1. CORS errors:
# config.yml
gateway:
  cors:
    enabled: true
    origins:
      - https://yourdomain.com
      - http://localhost:*

LLM Provider Errors

# Test API connection
curl https://gpt.qt.cool/v1/models \
  -H "Authorization: Bearer ${OPENAI_API_KEY}"

# Verify config
openclaw config get llm

# Switch provider
openclaw config set llm.provider openai-compatible
openclaw config set llm.base_url https://api.openai.com/v1

Daemon Service Issues (Windows)

If gateway install fails on Windows:

# Use daemon start instead (doesn't require schtasks)
openclaw gateway start

# Or use Docker
docker run -d -p 3000:3000 \
  -v ~/.openclaw:/root/.openclaw \
  ghcr.io/1186258278/openclaw-chinese:latest

Memory/Performance Issues

# Check resource usage
openclaw gateway status --verbose

# Limit memory (Node.js)
export NODE_OPTIONS="--max-old-space-size=4096"
openclaw gateway restart

# Clear cache
openclaw cache clear

Update Issues

# Force reinstall
npm uninstall -g @qingchencloud/openclaw-zh
npm install -g @qingchencloud/openclaw-zh@latest

# Clear npm cache if needed
npm cache clean --force

Uninstallation

# Stop services
openclaw gateway stop
openclaw gateway uninstall  # If installed as service

# Uninstall package
npm uninstall -g @qingchencloud/openclaw-zh

# Remove config (optional)
rm -rf ~/.openclaw

Additional Resources

FAQ

What does the openclaw-chinese-ai-assistant skill do?

OpenClaw Chinese localized AI assistant platform with CLI, dashboard, multi-platform chat integration (WhatsApp/Telegram/Discord), and LLM provider support

How do I install openclaw-chinese-ai-assistant?

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

Which AI agents can use openclaw-chinese-ai-assistant?

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-chinese-ai-assistant 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-chinese-ai-assistant?

It is published by reason-machines in reason-machines/hermes-skills. It has 173 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

Expert in deploying, configuring, and using Hermes WebUI—a web interface for Hermes Agent with persistent memory, scheduled jobs, and multi-platform messaging.

267 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 data & databases skills

View category →

supabase-postgres-best-practices

supabase/agent-skills

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pgcron, pgmq), vector/semantic search (pgvector), and restoring dumps (pgrestore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.

OfficialData & Databases462.2K installs

prisma-client-api

prisma/skills

Prisma Client API reference covering model queries, filters, operators, and client methods. Use when writing database queries, using CRUD operations, filtering data, or configuring Prisma Client. Triggers on "prisma query", "findMany", "create", "update", "delete", "$transaction".

OfficialData & Databases393.5K installs

prisma-database-setup

prisma/skills

Deprecated compatibility name for prisma-orm-setup. Use only when a user or existing integration explicitly invokes prisma-database-setup; otherwise select prisma-orm-setup.

OfficialData & Databases392.3K installs

prisma-cli

prisma/skills

Prisma ORM 7 CLI reference for existing Prisma 7 applications or explicitly selected Prisma 7 workflows. Covers prisma init, generate, migrate, db, dev, studio, and mcp. For setup, connection repair, or Prisma 8, use prisma-orm-setup; not the Prisma Platform CLI.

OfficialData & Databases390.8K installs

prisma-postgres

prisma/skills

Deprecated compatibility name for prisma-postgres-setup. Use only when a user or existing integration explicitly invokes prisma-postgres; otherwise select prisma-postgres-setup.

OfficialData & Databases384.4K installs

prisma-driver-adapter-implementation

prisma/skills

Required reference for Prisma ORM 7 SQL driver adapter work. Use when implementing or modifying adapters, adding database drivers, or touching SqlDriverAdapter, Transaction, savepoint, result mapping, or DriverAdapterError behavior. Covers current transaction lifecycle, optional savepoint hooks, original database-error preservation, and verification.

OfficialData & Databases378.9K installs