LiveKit Agents - Latitude Docs

Overview

This guide shows you how to send traces from a LiveKit Agents application to Latitude. LiveKit Agents ships with built-in OpenTelemetry support and owns its own tracer provider. Instead of bootstrapping telemetry with the Latitude class, you attach a LatitudeSpanProcessor to LiveKit’s provider — Latitude then receives the same spans LiveKit emits for LLM, agent, and tool activity. This works the same way for the Python (livekit-agents) and Node.js (@livekit/agents) SDKs.

You’ll keep building your LiveKit agent exactly as you do today. Latitude observes the LLM spans the framework already produces.

Requirements

A Latitude account and API key
A Latitude project slug
A project that uses LiveKit Agents (livekit-agents or @livekit/agents)

Steps

Install

Python
TypeScript

pip install latitude-telemetry "livekit-agents[openai]"

npm install @latitude-data/telemetry @opentelemetry/sdk-trace-node

Build a tracer provider, add the LatitudeSpanProcessor, and hand the provider to LiveKit inside your entrypoint.

Python
TypeScript

import os

from livekit.agents import AgentSession, JobContext
from livekit.agents.telemetry import set_tracer_provider
from opentelemetry.sdk.trace import TracerProvider

from latitude_telemetry import LatitudeSpanProcessor


def setup_latitude_telemetry():
    provider = TracerProvider()
    provider.add_span_processor(
        LatitudeSpanProcessor(
            os.environ["LATITUDE_API_KEY"],
            os.environ["LATITUDE_PROJECT_SLUG"],
        )
    )
    set_tracer_provider(provider)


async def entrypoint(ctx: JobContext):
    setup_latitude_telemetry()

    session = AgentSession(
        # ... your STT / LLM / TTS configuration
    )
    # ... start your agent as usual

import { telemetry, type JobContext } from "@livekit/agents"
import { LatitudeSpanProcessor } from "@latitude-data/telemetry"
import { NodeTracerProvider } from "@opentelemetry/sdk-trace-node"

function setupLatitudeTelemetry() {
  const provider = new NodeTracerProvider({
    spanProcessors: [
      new LatitudeSpanProcessor(
        process.env.LATITUDE_API_KEY!,
        process.env.LATITUDE_PROJECT_SLUG!,
      ),
    ],
  })
  telemetry.setTracerProvider(provider)
}

export default async function entrypoint(ctx: JobContext) {
  setupLatitudeTelemetry()

  // ... build and start your AgentSession as usual
}

What you get

LiveKit’s LLM spans carry both gen_ai.* metadata and the conversation content in custom lk.* attributes. Latitude parses both, so each LLM turn shows up with:

Model and provider — from gen_ai.request.model / gen_ai.provider.name
Token usage and latency — input/output tokens, time-to-first-token
Input messages — the chat context (system prompt, user turns, prior tool calls and results)
Output messages — the assistant response text and any tool calls the model emitted
Tool definitions — the function tools available to the agent

LiveKit produces many non-LLM spans (STT, TTS, VAD). By default the span processor’s smart filter forwards only LLM-relevant spans to keep your traces focused. To export every LiveKit span, pass options:

from latitude_telemetry import LatitudeSpanProcessor, LatitudeSpanProcessorOptions

LatitudeSpanProcessor(
    api_key,
    project,
    LatitudeSpanProcessorOptions(disable_smart_filter=True),
)

Seeing Your Traces

Once connected, traces appear automatically in Latitude:

Open your project in the Latitude dashboard
Each agent turn shows the LLM call with its input/output conversation
Token usage and latency are aggregated at every level

​Overview

​Requirements

​Steps

​What you get

​Seeing Your Traces

Overview

Requirements

Steps

What you get

Seeing Your Traces