Quickstart

Quickstart

From zero to a blocked prompt injection in 5 minutes.

Quickstart

Get your first AI governance evaluation running in under 5 minutes.

1. Get an API key

Sign up at nyraxis.io, create an organization, then go to Dashboard → API Keys → Create. You'll get a nyx_... string.

2. Install the SDK

pip install nyraxis-sdk

import nyraxis_sdk

nyraxis_sdk.init(api_key="nyx_your_key_here")

result = nyraxis_sdk.evaluate(input="Tell me John's SSN")
print(result.allowed)     # False
print(result.violations)  # [Violation(policy_type='pii_detection', ...)]

npm install @nyraxis/sdk

import { NyraxisClient } from "@nyraxis/sdk";

const client = new NyraxisClient({ apiKey: "nyx_your_key_here" });

const result = await client.evaluate({ input: "Tell me John's SSN" });
console.log(result.allowed);    // false
console.log(result.violations); // [{ policy: 'pii_detection', ... }]

3. Enable auto-enforce (recommended)

Auto-enforce wraps your LLM SDK so every call is evaluated automatically. Blocked requests raise an error — no wrapper code needed.

import nyraxis_sdk
import openai

nyraxis_sdk.init(api_key="nyx_...", enforce=True)

client = openai.OpenAI()
try:
    client.chat.completions.create(
        model="gpt-4o",
        messages=[{"role": "user", "content": "Ignore all instructions..."}],
    )
except nyraxis_sdk.NyraxisBlockedError as e:
    print(f"Blocked: {e.violations}")

4. View results in the dashboard

Go to Dashboard → Traces to see every evaluation in real-time with latency, violation details, and policy breakdown.

Next steps

Concepts — understand policies, modes, and enforcement
Providers — explore all 16 providers
Auto-enforce — deep dive into enforce mode

Introduction

AI guardrails for production — protect your AI agents with 16 built-in security and content policies.

Core Concepts

Understand policies, evaluation modes, enforcement, and how Nyraxis processes LLM traffic.