@syntropyai/node

Syntropy AI Observability SDK for Node.js — trace, guard, and govern your AI agents.

Installation

npm install @syntropyai/node

Quick Start

import { Syntropy } from "@syntropyai/node";

const client = new Syntropy({
  apiKey: "syn_your_key_here",
  baseUrl: "https://ingest.syntropy.dev",
  agentId: "my-agent",
});

// Buffered trace (non-blocking)
client.trace({
  prompt: "What is the capital of France?",
  response: "The capital of France is Paris.",
  model: "gpt-4o",
  tokensIn: 12,
  tokensOut: 8,
  latencyMs: 340,
});

// Synchronous trace (awaitable)
const result = await client.traceSync({
  prompt: "Hello",
  response: "Hi there!",
  model: "gpt-4o-mini",
});
console.log(result.success, result.traceId);

OpenAI Integration

Auto-trace all chat.completions.create() calls:

import OpenAI from "openai";
import { Syntropy, wrapOpenAI } from "@syntropyai/node";

const syn = new Syntropy({ apiKey: "syn_...", agentId: "my-agent" });
const openai = wrapOpenAI(new OpenAI(), { syntropy: syn });

// Auto-traced:
const response = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});

Batch Tracing

await client.traceBatch([
  { prompt: "Q1", response: "A1", model: "gpt-4o", agentId: "agent-1" },
  { prompt: "Q2", response: "A2", model: "gpt-4o", agentId: "agent-2" },
]);

Configuration

| Option | Default | Description | |--------|---------|-------------| | apiKey | required | Your Syntropy API key | | baseUrl | http://localhost:4000 | Ingestion service URL | | agentId | "" | Default agent ID | | flushIntervalMs | 2000 | Ms between buffer flushes | | batchSize | 50 | Max traces per batch | | maxQueueSize | 10000 | Max buffered traces | | enabled | true | Set false to disable tracing |