Instrument TypeScript and JavaScript agents

This guide shows you how to install the AI Observability JavaScript SDK, instrument an LLM call, and verify that generation data reaches AI Observability.

Note
AI Observability is referred to as “Sigil” in SDKs, package names, and configuration. For example, the npm package is @grafana/sigil-sdk-js.

Before you begin

A running AI Observability instance or Grafana Cloud stack with AI Observability enabled.
Node.js 22 or later.
Your AI Observability generation export endpoint URL.
A Cloud Access Policy Token with the sigil:write scope. Refer to Collect credentials from Grafana Cloud for step-by-step instructions.

Install the SDK

npm install @grafana/sigil-sdk-js

Use a framework integration

If you use LangChain, LangGraph, OpenAI Agents, LlamaIndex, Google ADK, or Vercel AI SDK, import the framework sub-module for automatic generation capture:

@grafana/sigil-sdk-js/langchain
@grafana/sigil-sdk-js/langgraph
@grafana/sigil-sdk-js/openai-agents
@grafana/sigil-sdk-js/llamaindex
@grafana/sigil-sdk-js/google-adk
@grafana/sigil-sdk-js/vercel-ai-sdk

Each integration attaches callbacks or hooks that capture generations automatically. Refer to Instrument agents with frameworks for setup details.

Capture a generation manually

To instrument calls without a framework:

import { SigilClient } from "@grafana/sigil-sdk-js";

const client = new SigilClient({
  generationExport: {
    protocol: "http",
    endpoint: "<SIGIL_ENDPOINT>",
    auth: { mode: "tenant", tenantId: "<TENANT_ID>" },
  },
});

await client.startGeneration(
  {
    conversationId: "conv-1",
    model: { provider: "openai", name: "gpt-4o" },
  },
  async (recorder) => {
    recorder.setResult({
      output: [{ role: "assistant", content: "Hello from Sigil" }],
    });
  },
);

await client.shutdown();

Replace SIGIL_ENDPOINT and TENANT_ID with your values.

Use environment variables instead

If you set SIGIL_ENDPOINT, SIGIL_PROTOCOL, SIGIL_AUTH_MODE, SIGIL_AUTH_TENANT_ID, and SIGIL_AUTH_TOKEN, the SDK reads them at client construction. Refer to Configure your SDK.

const client = new SigilClient();

Use a provider helper

The SDK includes helpers for OpenAI, Anthropic, and Gemini. For example, with OpenAI:

import { SigilClient, openai } from "@grafana/sigil-sdk-js";

const sigil = new SigilClient({
  generationExport: {
    protocol: "http",
    endpoint: "<SIGIL_ENDPOINT>",
    auth: { mode: "tenant", tenantId: "<TENANT_ID>" },
  },
});

const response = await openai.chat.completions.create(sigil, openaiClient, {
  model: "gpt-4o",
  messages: [{ role: "user", content: "What is observability?" }],
});

await sigil.shutdown();

Configure authentication in code

For Grafana Cloud, use basic auth with your Cloud Access Policy Token:

const client = new SigilClient({
  generationExport: {
    protocol: "http",
    endpoint: "<SIGIL_ENDPOINT>",
    auth: {
      mode: "basic",
      tenantId: "<INSTANCE_ID>",
      basicPassword: "<API_KEY>",
    },
  },
});

Set up traces and metrics

The SDK emits OpenTelemetry spans and metrics alongside generation data. To export them, configure a TracerProvider and MeterProvider in your application before creating the Sigil client. Without this, traces and metrics are silently lost.

Refer to Set up traces and metrics for Grafana Cloud OTLP options and SDK configuration for setup snippets.

Verify data

Open the AI Observability plugin in Grafana and navigate to Conversations. Your generation should appear within a few seconds. Check your Traces and Metrics data sources for SDK-emitted spans and metrics.