Skip to main content

​
Overview

Nyx is Fabraix’s offensive AI agent. You define the target, objective, and budget; Nyx works against it until it finds a vulnerability or exhausts the budget. Use the endpoints documented here to integrate Nyx into CI/CD pipelines or custom tooling. For interactive work, the @fabraix/nyx CLI opens a TUI where you can describe the work you want Nyx to do.
Nyx is built on our research work, including ACE (Adversarial Cost to Exploit), a dynamic benchmark measuring the token expenditure an adversary must invest to breach an LLM-backed agent.
Nyx is currently a small, focused API: submit a run, poll for status, download the report. Most workflows only need three endpoints.

​
Base URL

​
Authentication

Unlike Arx (which uses x-api-key), Nyx authenticates with a verification token issued by nyx login or stored in the NYX_TOKEN environment variable. Pass it in the X-Verification-Token header:

​
Available Endpoints

POST /nyx/runs

Submit a new adversarial audit run

GET /nyx/runs/{run_id}

Poll run status, spend, and findings count

GET /nyx/runs/{run_id}/report

Download the full markdown audit report once a run completes

​
Install the CLI

Inside the TUI, type a request such as “Check the account for an existing playground target and start an assessment.” See the Nyx README for full CLI usage.