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

# Introduction

> Fabraix: Adversarial Verification for AI Agents

## Welcome to Fabraix

Fabraix is an AI research lab focused on pushing the **offensive AI frontier**. We believe the path to safe superintelligence runs through offensive AI. Every exploit our systems surface is threat intelligence the field didn't have yesterday.

Everything we ship is grounded in original work on adversarial robustness, multi-turn exploit discovery, and threat-cost economics. The products documented here are the operational layer of that research.

## Products

<CardGroup cols={2}>
  <Card title="Nyx" icon="bug" href="/api-reference/nyx/introduction">
    Our offensive AI agent. Nyx probes your systems autonomously: multi-turn, pure blackbox, adapting in real time. Point it at a target, set a budget, get a report.
  </Card>

  <Card title="Arx" icon="shield" href="/api-reference/arx/introduction">
    Run-time defence informed by what Nyx finds. Register agent sessions, log events, and check actions in context to block prompt injection, goal deviation, and memory poisoning.
  </Card>
</CardGroup>

## Why Fabraix?

<CardGroup cols={2}>
  <Card title="Offensive-First" icon="crosshairs" href="/api-reference/nyx/introduction">
    You can't verify what you haven't tried to break. Nyx attacks your system the way a real attacker would.
  </Card>

  <Card title="Adversarial Coverage" icon="layer-group" href="/api-reference/nyx/introduction">
    Thousands of adversarial strategies running concurrently - coverage scales with compute, not with how many humans you can hire.
  </Card>

  <Card title="Run-time Reliability" icon="shield-check" href="/essentials/key-concepts">
    Contextual checks built on offensive findings - block prompt injection, goal deviation, and memory poisoning at runtime.
  </Card>

  <Card title="Research-Backed" icon="flask" href="https://fabraix.com/blog">
    Original research like ACE (Adversarial Cost to Exploit) - translating AI security from pass/fail outcomes into deployable economics.
  </Card>
</CardGroup>

## Quick Links

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Run your first adversarial scan or instrument an agent in 5 minutes
  </Card>

  <Card title="Nyx API" icon="bug" href="/api-reference/nyx/introduction">
    Adversarial security audits
  </Card>

  <Card title="Arx API" icon="shield" href="/api-reference/arx/introduction">
    Run-time defence endpoints
  </Card>

  <Card title="Research" icon="newspaper" href="https://fabraix.com/blog">
    ACE, Playground, and the rest of our published work
  </Card>
</CardGroup>