SDK & Examples

We provide official client libraries to intercept LLM calls, calculate costs, scan prompts, and trigger kill-switches. Our SDKs run locally with asynchronous caching to ensure sub-millisecond overhead on your application's hot path.

Node.js SDK

Install via npm:

npm install @rakshex/sdk

Usage example with OpenAI:

import { Rakshex } from '@rakshex/sdk';
import OpenAI from 'openai';

const RaksHex = new RaksHex({ apiKey: process.env.RAKSHEX_API_KEY });
const openai = RaksHex.wrap(new OpenAI());

// The wrapped client automatically reports costs, attributes usage, 
// and scans for prompt injections in the background.
const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'What is the cost of capital?' }],
  user: 'user_12938' // Essential for per-user cost tracking
});

Python SDK

Install via pip:

pip install RaksHex-sdk

Usage example with Anthropic:

from rakshex import Rakshex
from anthropic import Anthropic

RaksHex = RaksHex(api_key="your_api_key")
client = Anthropic()

# Wrap the client
wrapped_client = RaksHex.wrap(client)

response = wrapped_client.messages.create(
    model="claude-3-5-sonnet-20241022",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Analyze code security."}],
    metadata={"user_id": "usr_9921"}
)