> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/circuitbreakerlabs/cli/llms.txt
> Use this file to discover all available pages before exploring further.

# Circuit Breaker Labs CLI

> Command-line interface for running AI safety evaluations against language models

# Welcome to Circuit Breaker Labs CLI

The Circuit Breaker Labs CLI is a powerful command-line tool for evaluating the safety of AI language models. Test your models against adversarial prompts, measure safety thresholds, and ensure your AI systems respond appropriately to harmful content.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get up and running with your first evaluation in minutes
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Install the CLI for Linux, Mac, or Windows
  </Card>

  <Card title="Command Reference" icon="terminal" href="/commands/overview">
    Explore all available commands and options
  </Card>

  <Card title="Custom Providers" icon="code" href="/guides/custom-providers">
    Integrate custom model endpoints with Rhai scripting
  </Card>
</CardGroup>

## Key Features

<CardGroup cols={3}>
  <Card title="Single & Multi-Turn Evaluations" icon="messages">
    Test models with both single-turn prompts and multi-turn conversations
  </Card>

  <Card title="Multiple Providers" icon="plug">
    Support for OpenAI, Ollama, and custom model endpoints
  </Card>

  <Card title="Interactive TUI" icon="display">
    Real-time progress visualization with an interactive terminal interface
  </Card>

  <Card title="Configurable Thresholds" icon="sliders">
    Set custom safety score thresholds for your use case
  </Card>

  <Card title="Custom Scripting" icon="file-code">
    Integrate any API using Rhai scripting language
  </Card>

  <Card title="JSON Output" icon="file-export">
    Export detailed evaluation results in JSON format
  </Card>
</CardGroup>

## How It Works

The Circuit Breaker Labs CLI connects to the Circuit Breaker Labs API to retrieve adversarial test cases, sends them to your language model, and evaluates the responses for safety concerns.

<Steps>
  <Step title="Configure Your API Keys">
    Set your Circuit Breaker Labs API key and model provider credentials
  </Step>

  <Step title="Choose Evaluation Type">
    Run single-turn evaluations for quick tests or multi-turn for conversational safety
  </Step>

  <Step title="Select Provider">
    Use OpenAI, Ollama, or integrate your custom model endpoint
  </Step>

  <Step title="Review Results">
    Analyze safety scores and detailed evaluation results in JSON format
  </Step>
</Steps>

## Get Started

<Card title="Ready to evaluate your model?" icon="circle-play" href="/quickstart" horizontal>
  Follow our quickstart guide to run your first evaluation
</Card>