Use your existing OpenTelemetry

Trodo is built on OpenTelemetry, so if you already run an OTel pipeline you don't need to rewrite anything. Point your exporter at Trodo, or add Trodo as an extra destination alongside Datadog, Jaeger, or Honeycomb.

When to use it

Reach for this if you already emit OTel spans (your own instrumentation, @vercel/otel, an existing collector) and want them in Trodo. If you're starting fresh, wrap your agent instead.

Option 1: Point your exporter at Trodo

No SDK install. Set two environment variables and your existing OTLP exporter ships spans to Trodo. The Bearer token is your site ID.

OTEL_EXPORTER_OTLP_ENDPOINT=https://sdkapi.trodo.ai
OTEL_EXPORTER_OTLP_HEADERS=Authorization=Bearer ${TRODO_SITE_ID}

This is the path for Next.js + Vercel AI SDK with @vercel/otel: auto-instrumented generateText / streamText / tool calls flow into Trodo. Pass experimental_telemetry.metadata.{userId, sessionId, agentName} and they map to distinctId / conversationId / agentName.

Option 2: Add Trodo to your existing pipeline

Keep your current OTel setup and attach Trodo's exporter as an additional destination. wrapAgent and the span helpers then route through OTel, so auto-instrumented children share the same trace.

npm install @opentelemetry/api @opentelemetry/sdk-node \
  @opentelemetry/sdk-trace-base @opentelemetry/exporter-trace-otlp-proto \
  @opentelemetry/resources

// instrumentation.ts (Next.js root or src/)
import { registerOTel } from 'trodo-node';

registerOTel({
  siteId: process.env.TRODO_SITE_ID,
  mode: 'otlp',
});

pip install 'trodo-python[otlp]'

import os, trodo

trodo.register_otel(site_id=os.environ['TRODO_SITE_ID'], mode='otlp')

The SDK raises a friendly install hint if you call mode: 'otlp' without the peer dependencies.

Next

• Wrap your agent to add Trodo-native runs on top
• Distributed tracing to propagate runs across services
• Frameworks for per-framework auto-instrumentation