Quickstart
First trace in five minutes
Create a project, install the SDK, wrap your LLM client, and see traces in the dashboard.
1. Create a project
Sign in to the admin dashboard and create a project. Copy the ingest API key (starts with pu-).
2. Install the SDK
npm install @puse/sdk # or pnpm add @puse/sdk
3. Wrap your client
One line per provider. Streaming works out of the box.
import Anthropic from "@anthropic-ai/sdk";
import { createPuse } from "@puse/sdk";
const puse = createPuse({ apiKey: "pu-..." });
const anthropic = puse.wrapAnthropic(new Anthropic());
// use the client exactly as before — streaming included.
// every call is traced: model, tokens, cost, latency, errors.
const stream = await anthropic.messages.create({
model: "claude-sonnet-4-20250514",
max_tokens: 1024,
messages: [{ role: "user", content: "…" }],
stream: true,
});4. Verify traces
Make a few LLM calls, then open your project in the dashboard. You should see requests, latency, cost, and any errors within seconds.