# 🦞 Claw Setup ### Professional AI Agent Deployment Made Simple **End-to-end setup of OpenClaw, NanoBot, PicoClaw, ZeroClaw, or NanoClaw with security hardening and personal customization** ---

✨ Autonomously developed by GLM 5 Advanced Coding Model

⚠️ Disclaimer: Test in a test environment prior to using on any live system

---

## Overview Claw Setup handles the complete deployment of AI Agent platforms from the Claw family - from selection to production - with security best practices and personalized configuration through interactive brainstorming. ``` ┌─────────────────────────────────────────────────────────────────┐ │ CLAW SETUP WORKFLOW │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ Phase 1 Phase 2 Phase 3 Phase 4 │ │ ──────── ──────── ──────── ──────── │ │ │ │ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ │ │ │ SELECT │────►│ INSTALL │────►│CUSTOMIZE│────►│ DEPLOY │ │ │ └─────────┘ └─────────┘ └─────────┘ └─────────┘ │ │ │ │ │ │ │ │ ▼ ▼ ▼ ▼ │ │ Compare Clone & Brainstorm Systemd │ │ platforms harden your use case & monitor │ │ security │ │ │ │ ┌─────────────────────────────────────────────────────────────┐│ │ │ SUPPORTED PLATFORMS ││ │ │ ││ │ │ 🦞 OpenClaw Full-featured, 1700+ plugins, 215K stars ││ │ │ 🤖 NanoBot Python, 4K lines, research-ready ││ │ │ 🦐 PicoClaw Go, <10MB, $10 hardware ││ │ │ ⚡ ZeroClaw Rust, <5MB, 10ms startup ││ │ │ 💬 NanoClaw TypeScript, WhatsApp focused ││ │ │ ││ │ └─────────────────────────────────────────────────────────────┘│ │ │ └─────────────────────────────────────────────────────────────────┘ ``` ## Platform Comparison ``` ┌─────────────────────────────────────────────────────────────────┐ │ PLATFORM COMPARISON │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ Metric OpenClaw NanoBot PicoClaw ZeroClaw NanoClaw │ │ ───────────────────────────────────────────────────────────── │ │ Language TS Python Go Rust TS │ │ Memory >1GB ~100MB <10MB <5MB ~50MB │ │ Startup ~500s ~30s ~1s <10ms ~5s │ │ Binary Size ~28MB N/A ~8MB 3.4MB ~15MB │ │ GitHub Stars 215K+ 22K 15K 10K 5K │ │ Plugins 1700+ ~50 ~20 ~15 ~10 │ │ Learning Medium Easy Easy Medium Easy │ │ │ │ BEST FOR: │ │ ───────── │ │ OpenClaw → Full desktop AI, extensive integrations │ │ NanoBot → Research, customization, Python developers │ │ PicoClaw → Embedded, low-resource, $10 hardware │ │ ZeroClaw → Maximum performance, security-critical │ │ NanoClaw → WhatsApp automation, messaging bots │ │ │ └─────────────────────────────────────────────────────────────────┘ ``` ## Decision Flowchart ``` ┌─────────────────┐ │ Need AI Agent? │ └────────┬────────┘ │ ▼ ┌───────────────────────┐ │ Memory constrained? │ │ (<1GB RAM available) │ └───────────┬───────────┘ ┌─────┴─────┐ │ │ YES NO │ │ ▼ ▼ ┌──────────────┐ ┌──────────────────┐ │ Need <10MB? │ │ Want plugins? │ └──────┬───────┘ └────────┬─────────┘ ┌─────┴─────┐ ┌─────┴─────┐ │ │ │ │ YES NO YES NO │ │ │ │ ▼ ▼ ▼ ▼ ┌────────┐ ┌────────┐ ┌────────┐ ┌────────┐ │ZeroClaw│ │PicoClaw│ │OpenClaw│ │NanoBot │ │ (Rust) │ │ (Go) │ │ (Full) │ │(Python)│ └────────┘ └────────┘ └────────┘ └────────┘ ``` ## Quick Start ### Option 1: Interactive Setup (Recommended) ``` "Setup Claw AI assistant on my server" "Help me choose and install an AI agent platform" ``` ### Option 2: Direct Platform Selection ``` "Setup OpenClaw with all security features" "Install ZeroClaw on my VPS" "Deploy NanoBot for research use" ``` ## Installation Guides ### OpenClaw (Full Featured) ```bash # Prerequisites sudo apt update && sudo apt install -y nodejs npm git # Clone official repo git clone https://github.com/openclaw/openclaw.git cd openclaw # Install dependencies npm install # Run setup wizard npm run setup # Configure environment cp .env.example .env nano .env # Add your API keys # Start npm run start ``` ### NanoBot (Python Lightweight) ```bash # Quick install via pip pip install nanobot-ai # Initialize nanobot onboard # Configure (~/.nanobot/config.json) { "providers": { "openrouter": { "apiKey": "sk-or-v1-xxx" } }, "agents": { "defaults": { "model": "anthropic/claude-opus-4-5" } } } # Start gateway nanobot gateway ``` ### PicoClaw (Go Ultra-Light) ```bash # Download latest release wget https://github.com/sipeed/picoclaw/releases/latest/download/picoclaw-linux-amd64 chmod +x picoclaw-linux-amd64 sudo mv picoclaw-linux-amd64 /usr/local/bin/picoclaw # Create config mkdir -p ~/.config/picoclaw picoclaw config init # Start picoclaw gateway ``` ### ZeroClaw (Rust Minimal) ```bash # Download latest release wget https://github.com/zeroclaw-labs/zeroclaw/releases/latest/download/zeroclaw-linux-amd64 chmod +x zeroclaw-linux-amd64 sudo mv zeroclaw-linux-amd64 /usr/local/bin/zeroclaw # Initialize config zeroclaw init # Migrate from OpenClaw (optional) zeroclaw migrate openclaw --dry-run # Start zeroclaw gateway ``` ## Security Hardening ### 1. Secrets Management ```bash # Never hardcode API keys - use environment variables export ANTHROPIC_API_KEY="your-key" export OPENROUTER_API_KEY="your-key" # Add to shell profile for persistence echo 'export ANTHROPIC_API_KEY="your-key"' >> ~/.bashrc # Use encrypted config files mkdir -p ~/.config/claw chmod 700 ~/.config/claw ``` ### 2. Network Security ```bash # Bind to localhost only # config.json: { "server": { "host": "127.0.0.1", "port": 3000 } } # Use nginx reverse proxy for external access sudo certbot --nginx -d claw.yourdomain.com ``` ### 3. Systemd Hardened Service ```bash # /etc/systemd/system/claw.service [Unit] Description=Claw AI Assistant After=network.target [Service] Type=simple User=claw Group=claw WorkingDirectory=/opt/claw ExecStart=/usr/local/bin/claw gateway Restart=on-failure # Security hardening NoNewPrivileges=true PrivateTmp=true ProtectSystem=strict ProtectHome=true ReadWritePaths=/opt/claw/data Environment="ANTHROPIC_API_KEY=%i" [Install] WantedBy=multi-user.target ``` ```bash # Enable service sudo systemctl daemon-reload sudo systemctl enable --now claw ``` ## Brainstorm Session After installation, we'll explore your needs: ### 🎯 Use Case Discovery ``` Q: What tasks should your AI handle? □ Code assistance & development □ Research & information gathering □ Personal productivity (calendar, reminders) □ Content creation & writing □ Data analysis & visualization □ Home automation □ Customer support / chatbot □ Other: _______________ ``` ### 🤖 Model Selection ``` Q: Which AI model(s) to use? □ Claude (Anthropic) - Best reasoning □ GPT-4 (OpenAI) - General purpose □ Gemini (Google) - Multimodal □ Local models (Ollama) - Privacy-first □ OpenRouter - Multi-model access ``` ### 🔌 Integration Planning ``` Q: Which platforms to connect? Messaging: □ Telegram □ Discord □ WhatsApp □ Slack Calendar: □ Google □ Outlook □ Apple □ None Storage: □ Local □ Google Drive □ Dropbox □ S3 APIs: □ Custom REST APIs □ Webhooks □ Database connections ``` ### 🎨 Agent Personality ``` Q: How should your agent behave? Tone: Professional □ Casual □ Formal □ Playful □ Proactivity: □ Reactive (responds only when asked) □ Proactive (suggests, reminds, initiates) Memory: □ Session only (fresh each chat) □ Persistent (remembers everything) □ Selective (configurable retention) ``` ## Architecture ``` ┌─────────────────────────────────────────────────────────────────┐ │ DEPLOYED ARCHITECTURE │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ ┌─────────────┐ │ │ │ Internet │ │ │ └──────┬──────┘ │ │ │ │ │ ┌───────▼───────┐ │ │ │ nginx/HTTPS │ │ │ │ (Reverse │ │ │ │ Proxy) │ │ │ └───────┬───────┘ │ │ │ │ │ ┌──────────────────────────┼──────────────────────────────┐ │ │ │ localhost │ │ │ │ ┌─────────┐ ┌─────────▼────────┐ ┌────────────┐ │ │ │ │ │ Config │ │ CLAW ENGINE │ │ Data │ │ │ │ │ │ ~/.config│ │ (Gateway) │ │ Storage │ │ │ │ │ │ /claw │ │ Port: 3000 │ │ ~/claw/ │ │ │ │ │ └─────────┘ └─────────┬────────┘ └────────────┘ │ │ │ │ │ │ │ │ │ ┌─────────────────┼─────────────────┐ │ │ │ │ │ │ │ │ │ │ │ ┌────▼────┐ ┌─────▼─────┐ ┌─────▼─────┐ │ │ │ │ │ LLM │ │ Tools │ │ Memory │ │ │ │ │ │ APIs │ │ Plugins │ │ Context │ │ │ │ │ │Claude/GPT│ │ Skills │ │ Store │ │ │ │ │ └─────────┘ └───────────┘ └───────────┘ │ │ │ │ │ │ │ └──────────────────────────────────────────────────────────┘ │ │ │ └─────────────────────────────────────────────────────────────────┘ ``` ## Post-Setup Checklist ``` □ API keys configured securely □ Network binding verified (localhost) □ Firewall configured □ SSL certificate installed (if external) □ Systemd service enabled □ Logs configured and rotating □ Backup strategy in place □ Test conversation successful □ Custom agents created □ Integrations connected ``` ---

Learn more about GLM 5 Advanced Coding Model

## AI Provider Configuration ### Supported Providers ``` ┌─────────────────────────────────────────────────────────────────┐ │ AI PROVIDER OPTIONS │ ├─────────────────────────────────────────────────────────────────┤ │ │ │ Direct Providers │ Gateways & Aggregators │ │ ───────────────── │ ────────────────────── │ │ • Anthropic (Claude) │ • OpenRouter (200+ models) │ │ • OpenAI (GPT-4, o1, o3) │ • Replicate │ │ • Google (Gemini 2.0) │ │ │ • Mistral │ Fast Inference │ │ • DeepSeek │ ─────────────── │ │ • xAI (Grok) │ • Groq (ultra-fast) │ │ │ • Cerebras (fastest) │ │ Local/Self-Hosted │ • Together AI │ │ ────────────────── │ │ │ • Ollama │ │ │ • LM Studio │ │ │ • vLLM │ │ │ │ └─────────────────────────────────────────────────────────────────┘ ``` ### Model Selection Options **Option A: Fetch from Provider** ```bash # Automatically fetch available models "Fetch available models from OpenRouter" "Show me Groq models" "What models are available via OpenAI?" ``` **Option B: Custom Model Input** ``` "Add custom model: my-org/fine-tuned-llama" "Configure local Ollama model: llama3.2:70b" "Use fine-tuned GPT: ft:gpt-4o:org:custom" ``` ### Multi-Provider Setup ```json { "providers": { "anthropic": { "apiKey": "${ANTHROPIC_API_KEY}" }, "openai": { "apiKey": "${OPENAI_API_KEY}" }, "google": { "apiKey": "${GOOGLE_API_KEY}" }, "openrouter": { "apiKey": "${OPENROUTER_API_KEY}" }, "groq": { "apiKey": "${GROQ_API_KEY}" }, "ollama": { "baseURL": "http://localhost:11434" } }, "models": { "default": "anthropic/claude-sonnet-4-5", "fast": "groq/llama-3.3-70b-versatile", "local": "ollama/llama3.2:70b" } } ``` ### Provider Comparison | Provider | Best For | Speed | Cost | |----------|----------|-------|------| | Claude | Reasoning, coding | Medium | $$$ | | GPT-4o | General purpose | Fast | $$$ | | Gemini | Multimodal | Fast | $$ | | Groq | Fastest inference | Ultra-fast | $ | | OpenRouter | Model variety | Varies | $-$$$ | | Ollama | Privacy, free | Depends on HW | Free | ---

Learn more about GLM 5 Advanced Coding Model