| title | Quick start |
|---|---|
| description | Generate your first OpenClaw stack in under 2 minutes |
The fastest way to get started with better-openclaw is using the interactive CLI wizard:
npx create-better-openclaw@latest<Info>
The wizard includes automatic dependency resolution—if you select n8n, it will automatically add PostgreSQL for you.
</Info>
- AI platforms (Ollama, Open WebUI, Dify)
- Databases (PostgreSQL, Redis, Qdrant)
- Automation (n8n, Home Assistant)
- Monitoring (Grafana, Prometheus)
- And many more
Or pick a preset to get started instantly (see below).
- Reverse proxy (none, Caddy, or Traefik)
- Domain name for auto-SSL
- AI providers (OpenAI, Anthropic, Google, etc.)
- GPU passthrough for AI services
- Monitoring dashboards
Port conflicts are detected automatically and services are reassigned to available ports.
```bash
cd my-openclaw-stack
docker compose up -d
```
Your entire OpenClaw infrastructure is now running!
Skip the wizard and generate a complete stack instantly with presets:
```bash Researcher # Web research with vector memory and scraping npx create-better-openclaw --preset researcher --yes ```# Monitoring, automation, and alerting
npx create-better-openclaw --preset devops --yes# Multi-model AI experimentation
npx create-better-openclaw --preset ai-playground --yes# Video and content creation tools
npx create-better-openclaw --preset creator --yes| Preset | Services | Memory | Use case |
|---|---|---|---|
| minimal | Redis | ~1 GB | Basic caching and state management |
| creator | FFmpeg, Remotion, MinIO, Redis | ~2 GB | Video creation and processing |
| researcher | Qdrant, SearXNG, Browserless, Redis | ~2.5 GB | Web research with vector memory |
| devops | n8n, PostgreSQL, Redis, Uptime Kuma, Grafana, Prometheus | ~3 GB | Monitoring and automation |
| ai-playground | Ollama, Open WebUI, Qdrant, LiteLLM, Redis | ~6 GB | Multi-model AI experimentation |
| coding-team | Claude Code, Codex, Redis, PostgreSQL | ~3 GB | AI coding agents with shared state |
| full-stack | All core services + all skill packs | ~8 GB | Complete OpenClaw superstack |
Perfect for CI/CD pipelines and automation scripts:
```bash Cherry-pick services npx create-better-openclaw \ --services postgresql,redis,n8n,grafana \ --proxy caddy \ --domain example.com \ --yes ```npx create-better-openclaw \
--preset researcher \
--ai-providers openai,anthropic,google \
--yesnpx create-better-openclaw \
--services postgresql,redis,n8n \
--proxy caddy \
--proxy-http-port 8080 \
--proxy-https-port 8443 \
--yesnpx create-better-openclaw \
--preset devops \
--dry-runnpx create-better-openclaw \
--preset minimal \
--yes \
--jsonList all 94 available services:
npx create-better-openclaw services listFilter by category:
npx create-better-openclaw services list --category databaseSee exactly what's included in a preset before generating:
npx create-better-openclaw presets info researcherThis shows:
- All included services with descriptions
- Skill packs included
- Estimated memory usage
- Service dependencies
Check your configuration before deploying:
```bash Validate services npx create-better-openclaw validate \ --services postgresql,redis,n8n ```npx create-better-openclaw validate \
--preset researchernpx create-better-openclaw validate \
--dir ./my-stackThe validator checks for:
- Port conflicts
- Missing dependencies
- Resource limits
- Configuration errors
Once your stack is generated, you can manage it with these commands:
```bash Add a service cd my-openclaw-stack npx create-better-openclaw add grafana ```npx create-better-openclaw remove grafananpx create-better-openclaw statusnpx create-better-openclaw updateDeploy your stack directly to Dokploy or Coolify:
npx create-better-openclaw deployFollow the interactive prompts to select your provider, enter your instance URL, and provide an API key.
For non-interactive deployment:
npx create-better-openclaw deploy \
--provider dokploy \
--url https://dokploy.example.com \
--api-key your-api-key