agentlens

One import. See where your LLM money goes. Get told exactly how to cut it.

AgentLens wraps the Anthropic and OpenAI TypeScript SDKs to capture cost and performance telemetry — without changing how your code works or adding any latency.

Install

npm install useagentlens

Quickstart

Anthropic

// Before
import Anthropic from "@anthropic-ai/sdk";

// After — one line change
import { Anthropic } from "useagentlens";

const client = new Anthropic({
  agentlensKey: "al_live_...",   // from useagentlens.com/settings
});

// Everything else stays the same
const msg = await client.messages.create({
  model: "claude-haiku-4-5-20251001",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello!" }],
});

OpenAI

// Before
import OpenAI from "openai";

// After — one line change
import { OpenAI } from "useagentlens";

const client = new OpenAI({
  agentlensKey: "al_live_...",   // from useagentlens.com/settings
});

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

Labelling requests

Tag your requests to group costs by feature, user session, or agent step:

const client = new Anthropic({
  agentlensKey: "al_live_...",   // from useagentlens.com/settings
  endpoint: "customer-support",      // groups costs by feature in the dashboard
  sessionId: userSessionId,          // tracks cost across a full conversation
  step: stepNumber,                  // tracks cost growth across agent steps
});

// Or override per-call without creating a new client
const step2Client = client.withOptions({ step: 2 });

How it works

• Your existing Anthropic/OpenAI API key is passed straight through — AgentLens never sees it
• After each API response, usage data is read and sent to the AgentLens ingest API asynchronously via fetch
• Zero latency added to your application
• If the AgentLens API is unreachable, events are silently dropped — your code always continues normally

Dashboard

Sign in at useagentlens.com to see:

• Total spend over time
• Cost breakdown by endpoint, model, and session
• P95 latency alongside average latency
• Actionable insights: system prompt bloat, model mismatch, agent loop explosion

Peer dependencies

@anthropic-ai/sdk and openai are optional peer dependencies — install only what you use:

npm install useagentlens @anthropic-ai/sdk   # Anthropic only
npm install useagentlens openai              # OpenAI only
npm install useagentlens @anthropic-ai/sdk openai  # Both

Debug mode

No API key? Print events to the console instead of sending them:

const client = new Anthropic({ agentlensDebug: true });

License

MIT