Getting Started

Cyberstrike is an AI-powered penetration testing agent that automates security assessments. This guide covers installation, authentication, and running your first scan.

System Requirements

Before installing Cyberstrike, verify your system meets these requirements:

Installing Cyberstrike

Choose your preferred installation method based on your operating system and package manager.

npm (Recommended)

1. Open your terminal
2. Run the installation command:

npm install -g @cyberstrike-io/cyberstrike@latest

3. Verify the installation:

cyberstrike --version

Bun Coming Soon

Bun support is not yet available.

Homebrew (macOS) Coming Soon

Homebrew support is not yet available.

curl (Linux/macOS)

Run the installation script:

curl -fsSL https://cyberstrike.io/install.sh | bash

iwr (Windows/Powershell)

Run the installation script:

iwr -useb https://cyberstrike.io/install.ps1 | iex

Docker

Authenticating with an AI Provider

Cyberstrike requires an AI provider to function. The following providers are supported:

Setting Up Authentication

1. Run the authentication command:

cyberstrike auth login

2. Select your provider from the list:

? Select provider
❯ OpenRouter (free tier available)
  Anthropic (API key from console.anthropic.com)
  OpenAI (ChatGPT Plus/Pro or API key)
  Google (API key from ai.google.dev)
  Ollama (local models)
  Other

3. Enter your API key when prompted

4. Verify your credentials:

cyberstrike auth list

Using Environment Variables

Set API keys as environment variables instead of storing them:

# Anthropic
export ANTHROPIC_API_KEY="sk-ant-..."

# OpenAI
export OPENAI_API_KEY="sk-..."

# Google
export GOOGLE_API_KEY="AI..."

# OpenRouter
export OPENROUTER_API_KEY="sk-or-..."

Add these to your shell profile (~/.bashrc, ~/.zshrc) for persistence.

Running Your First Scan

Starting Interactive Mode

Launch Cyberstrike in your target directory:

cd /path/to/target
cyberstrike

The terminal user interface (TUI) appears with:

• Input prompt at the bottom
• Response area in the center
• Status bar showing model and token usage

Executing a Quick Scan

Run a single command without entering interactive mode:

cyberstrike run "perform reconnaissance on example.com"

Selecting a Security Agent

Cyberstrike includes specialized agents for different assessment types:

# Web application security
cyberstrike --agent web-application

# Cloud infrastructure
cyberstrike --agent cloud-security

# Network penetration testing
cyberstrike --agent internal-network

# Bug bounty reconnaissance
cyberstrike --agent bug-hunter

Basic Configuration

Create a cyberstrike.json file in your project directory to set default options:

{
  "$schema": "https://cyberstrike.io/config.json",
  "model": "anthropic/claude-sonnet-4-20250514",
  "default_agent": "web-application"
}

When you run cyberstrike in this directory, it automatically loads these settings. The example above:

• Uses Claude Sonnet as the default AI model
• Starts with the web-application security agent

This eliminates the need to specify --model and --agent flags every time.

Configuration Hierarchy

Cyberstrike loads configuration from multiple sources in this order:

1. Command line arguments (highest priority)
2. Environment variables
3. Project config (cyberstrike.json)
4. User config (~/.config/cyberstrike/cyberstrike.json)
5. Default values (lowest priority)

For detailed configuration options, see the Configuration Reference.

Keyboard Shortcuts

Learn these shortcuts for efficient navigation:

Next Steps

Continue learning with these guides:

1. Configuration Reference - Customize Cyberstrike settings
2. AI Providers - Configure your preferred AI provider
3. Security Agents - Learn about specialized agents
4. CLI Commands - Complete command reference