Mastra Observability & Monitoring with OpenTelemetry

SigNoz announced support for Mastra observability through OpenTelemetry, enabling developers to instrument AI applications and export traces for real-time monitoring of model performance, latency, error rates, and usage trends. The integration allows users to correlate traces, logs, and metrics across AI workflows, set alerts, and improve application reliability. Developers can set up the monitoring by configuring an OpenTelemetry exporter with a SigNoz ingestion key and registering agents with telemetry enabled in their Mastra projects.

What is Mastra Observability? Mastra observability lets you instrument your AI applications using OpenTelemetry https://opentelemetry.io/ and export traces to SigNoz. This guide walks you through setting up Mastra monitoring so you get real-time visibility into model performance, latency, error rates, and usage trends across your Mastra applications. With full Mastra observability in SigNoz, you can correlate traces, logs, and metrics across AI workflows, set alerts on error rates and latency, and continuously improve the reliability of your Mastra applications. Prerequisites - A SigNoz Cloud account https://signoz.io/teams/ with an active ingestion key - Internet access to send telemetry data to SigNoz Cloud - Node.js v20.0 or higher - An API key from a supported Model Provider https://mastra.ai/en/models/providers Setting Up Mastra Observability with OpenTelemetry You can get the full Mastra installation instructions https://mastra.ai/en/docs/getting-started/installation . Step 1: Start the CLI Wizard Run the following command to start the interactive setup: npx create-mastra@latest yarn dlx create-mastra@latest pnpm create mastra@latest bun create mastra@latest Step 2: Add Your API key Add your API key to the .env file: OPENAI API KEY=<your-api-key This example uses OpenAI. Each LLM provider uses a unique name. See Model Capabilities for more information. Setup an Agent Step 1: Create an agent in your project. For example, create a file src/mastra/agents/chefAgent.ts : js import { openai } from "@ai-sdk/openai"; import { Agent } from "@mastra/core/agent"; export const chefAgent = new Agent { name: "chef-agent", instructions: "You are Michel, a practical and experienced home chef" + "You help people cook with whatever ingredients they have available.", model: openai "gpt-4o-mini" , } ; Step 2: Register the Agent with Mastra In your src/mastra/index.ts file, register the agent with telemetry enabled: js import { Mastra } from "@mastra/core"; import { chefAgent } from "./agents/chefAgent"; import { OtelExporter } from "@mastra/otel-exporter"; export const mastra = new Mastra { agents: { chefAgent }, observability: { configs: { otel: { serviceName: '<service-name ', exporters: new OtelExporter { provider: { signoz: { apiKey: process.env.SIGNOZ INGESTION KEY, region: 'us', // 'us' | 'eu' | 'in', } }, } , }, }, }, } ; is the name of your service <service name → Your SigNoz SIGNOZ INGESTION KEY ingestion key https://signoz.io/docs/ingestion/signoz-cloud/keys/ . Set the value as an environment variable.→ appropriate region region https://signoz.io/docs/ingestion/signoz-cloud/overview/ endpoint Step 3: Run Mastra Dev Server and Interact with Agent npm run dev You should see some output similar to this: Visit the playground url, and start chatting with the registered agent. All your interactions should be traced and sent to SigNoz under the traces tab. View Mastra Traces in SigNoz Once configured, your Mastra application automatically emits traces. Traces are available in SigNoz Cloud under the Traces tab: When you click on a trace in SigNoz, you'll see a detailed view of the trace, including all associated spans, along with their events and attributes. Mastra Observability Dashboard You can also check out our Mastra Dashboard https://signoz.io/docs/dashboards/dashboard-templates/mastra-dashboard/ which provides specialized visualizations for Mastra monitoring in your applications. The dashboard includes pre-built charts specifically tailored for LLM usage, along with import instructions to get started quickly.