Mastra LLM analytics installation

  1. Install dependencies

    Required
    Full working examples

    See the complete Node.js example on GitHub. If you're using the PostHog SDK wrapper instead, see the Node.js wrapper example.

    Install Mastra with the official @mastra/posthog exporter. Mastra's observability system sends traces to PostHog as $ai_generation events automatically.

    npm install @mastra/core @mastra/observability @mastra/posthog

  2. Configure Mastra with the PostHog exporter

    Required

    Initialize Mastra with an Observability config that uses the PosthogExporter. Pass your PostHog project token and host from your project settings.

    import { Mastra } from '@mastra/core'
    import { Agent } from '@mastra/core/agent'
    import { Observability } from '@mastra/observability'
    import { PosthogExporter } from '@mastra/posthog'
    

    const weatherAgent = new Agent({
      id: 'weather-agent',
      name: 'Weather Agent',
      instructions: 'You are a helpful assistant with access to weather data.',
      model: { id: 'openai/gpt-4o-mini' },
    })
    

    const mastra = new Mastra({
      agents: { weatherAgent },
      observability: new Observability({
        configs: {
          posthog: {
            serviceName: 'my-app',
            exporters: [
              new PosthogExporter({
                apiKey: '<ph_project_token>',
                host: 'https://us.i.posthog.com',
                defaultDistinctId: 'user_123', // fallback if no userId in metadata
              }),
            ],
          },
        },
      }),
    })

  3. Run your agent

    Required

    Use Mastra as normal. The PosthogExporter automatically captures $ai_generation events for each LLM call, including token usage, cost, latency, and the full conversation.

    Pass tracingOptions.metadata to generate() to attach per-request metadata. The userId field maps to PostHog's distinct ID, sessionId maps to $ai_session_id, and any other keys are passed through as custom event properties.

    const agent = mastra.getAgent('weatherAgent')
    

    const result = await agent.generate("What's the weather in Dublin?", {
      tracingOptions: {
        metadata: {
          userId: 'user_123', // becomes distinct_id
          sessionId: 'session_abc', // becomes $ai_session_id
          conversation_id: 'abc-123', // custom property
        },
      },
    })
    

    console.log(result.text)

    Note: If you want to capture LLM events anonymously, omit userId from tracingOptions.metadata and don't set defaultDistinctId. See our docs on anonymous vs identified events to learn more.

    You can expect captured $ai_generation events to have the following properties:

    PropertyDescription
    $ai_modelThe specific model, like gpt-5-mini or claude-4-sonnet
    $ai_latencyThe latency of the LLM call in seconds
    $ai_time_to_first_tokenTime to first token in seconds (streaming only)
    $ai_toolsTools and functions available to the LLM
    $ai_inputList of messages sent to the LLM
    $ai_input_tokensThe number of tokens in the input (often found in response.usage)
    $ai_output_choicesList of response choices from the LLM
    $ai_output_tokensThe number of tokens in the output (often found in response.usage)
    $ai_total_cost_usdThe total cost in USD (input + output)
    [...]See full list of properties

  4. Verify traces and generations

    Recommended
    Confirm LLM events are being sent to PostHog

    Let's make sure LLM events are being captured and sent to PostHog. Under LLM analytics, you should see rows of data appear in the Traces and Generations tabs.


    LLM generations in PostHog
    Check for LLM events in PostHog

  5. Next steps

    Recommended

    Now that you're capturing AI conversations, continue with the resources below to learn what else LLM Analytics enables within the PostHog platform.

    ResourceDescription
    BasicsLearn the basics of how LLM calls become events in PostHog.
    GenerationsRead about the $ai_generation event and its properties.
    TracesExplore the trace hierarchy and how to use it to debug LLM calls.
    SpansReview spans and their role in representing individual operations.
    Anaylze LLM performanceLearn how to create dashboards to analyze LLM performance.

Community questions

Was this page useful?

Questions about this page? or post a community question.