agentwatch

Lightweight OpenAI usage tracking for AgentWatch. Token counts, model, and latency are sent to AgentWatch after each response — prompts and completions never leave your server.

Install

npm install @itsmemyan/agentwatch

Usage

import OpenAI from "openai";
import { wrap } from "@itsmemyan/agentwatch";

const openai = wrap(new OpenAI(), {
  apiKey: "aw_live_...",   // Your AgentWatch API key
  agentId: "...",          // Agent ID from your AgentWatch dashboard
});

// Use exactly as before — tracking happens automatically
const response = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello" }],
});

// Streaming works too
const stream = await openai.chat.completions.create({
  model: "gpt-4o",
  messages: [{ role: "user", content: "Hello" }],
  stream: true,
});
for await (const chunk of stream) { /* ... */ }

What gets sent to AgentWatch

Only usage metadata — never your prompts or completions:

{
  "agent_id": "...",
  "model": "gpt-4o",
  "prompt_tokens": 12,
  "completion_tokens": 34,
  "latency_ms": 843,
  "success": true
}

Options

| Option | Type | Description | |--------|------|-------------| | apiKey | string | Your AgentWatch API key (aw_live_...) | | agentId | string | Agent ID from your dashboard | | ingestUrl | string | Override the ingest URL (optional) |

Find your API key and agent IDs at getagentwatch.com/dashboard/integrations.