Implementation Details

Documentation Index

Fetch the complete documentation index at: https://docs.uselemma.ai/llms.txt

Use this file to discover all available pages before exploring further.

​

Reference architecture

1. Application emits spans through Langfuse-supported instrumentation.
2. LangfuseSpanProcessor processes spans.
3. OpenTelemetry exporter sends processed spans to Lemma.

1. Application already emits OpenTelemetry-compatible spans through OpenInference, Arize, Braintrust, provider SDK instrumentation, or another OTel stack.
2. The existing tracer provider or collector keeps processing those spans.
3. Lemma is added as another OTLP trace export destination.

​

Destination models

• Lemma only: one Langfuse processor with Lemma exporter.
• Langfuse + Lemma: two Langfuse processors, one default and one with Lemma exporter.
• Existing OTel + Lemma: keep your current processor/exporter setup and add Lemma OpenTelemetry export.