Getting Started with ArmorClaw
Set up OpenClaw AI assistant with ArmorClaw security plugin for secure chat-based automation
Getting Started with ArmorClaw
OpenClaw is an AI assistant that works in Telegram, Slack, Discord, WhatsApp, and other chat applications. It can browse the web, manage files, run commands, control your calendar, send emails—it actually does things across any platform you use daily.
ArmorClaw adds enterprise-grade security: every action OpenClaw takes is verified with intent tokens, cryptographic proofs, and real-time policy enforcement before execution. Whether it's sending an email, accessing files, or making API calls, ArmorClaw ensures every action is authorized and auditable.
One Command Installation (macOS / Linux / Windows)
Get up and running in under 5 minutes with the ArmorClaw installer — handles everything automatically.
curl -fsSL https://armoriq.ai/install-armorclaw.sh | bashOn Windows, run this from Git Bash (or WSL).
What You'll Get
By the end of the installation, you'll have:
- OpenClaw agent framework running locally
- ArmorClaw plugin enabled with policy enforcement
- Telegram, Slack, or Discord bot integration
- Complete intent verification flow working
How It Works
Install
Run the one-line installer. It clones OpenClaw, applies security patches, installs the ArmorClaw plugin, and configures everything automatically.
Configure
Add your API keys — ArmorIQ, OpenAI/Gemini, and optionally Telegram/Slack for chat integration.
Run
Start the gateway and start using your secured AI agent via your preferred chat platform.
Prerequisites
Before you begin, ensure you have:
- Node.js v22 or higher
- pnpm package manager
- Git
- ArmorIQ API Key from platform.armoriq.ai → API Dashboard → API Keys
- OpenAI or Gemini API Key for LLM access
- Telegram Account (optional, for bot integration)
Architecture Overview
┌─────────────────────────────────────────────────────────┐
│ Telegram / Slack / Discord Bot │
│ (User Interface) │
└──────────────────────┬──────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ OpenClaw Gateway │
│ ┌─────────────────────────────────────────────────┐ │
│ │ ArmorIQ Plugin │ │
│ │ • Captures LLM plan (tool steps) │ │
│ │ • Requests intent token from IAP │ │
│ │ • Verifies each step before execution │ │
│ │ • Enforces policies │ │
│ └─────────────────────────────────────────────────┘ │
│ │
│ ┌─────────────────────────────────────────────────┐ │
│ │ Tool Execution │ │
│ │ • web_search, web_fetch │ │
│ │ • write_file, read_file │ │
│ │ • policy_update (if authorized) │ │
│ └─────────────────────────────────────────────────┘ │
└──────────────────────┬──────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ ArmorIQ Intent Access Proxy (IAP) │
│ • Issues cryptographic intent tokens │
│ • Verifies token validity │
│ • Step-by-step proof validation │
└──────────────────────┬──────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────┐
│ ArmorIQ Backend Services │
│ • Policy management and enforcement │
│ • Audit logs and compliance tracking │
│ • Organization and user management │
└─────────────────────────────────────────────────────────┘How It Works
- User sends prompt via Telegram, Slack, or Discord to the OpenClaw bot
- LLM creates plan with tool actions (e.g., web_search, write_file)
- ArmorIQ Plugin captures plan and requests intent token from IAP
- IAP issues token with cryptographic proofs for each step
- Before each tool execution, ArmorIQ Plugin verifies:
- Token validity with IAP
- Step proof matches tool call
- Active policies from Backend allow the action
- Tool executes only if all verifications pass
- Results returned to user via their chat platform
- Audit logs recorded in Backend Services for compliance
Support
- Documentation: https://docs.armoriq.ai
- GitHub Issues: https://github.com/armoriq/armorclaw/issues
- Email: license@armoriq.io
Ready to get started? Proceed to Installation →