06COMPATIBLE

Works with your stack

Currai speaks the Langfuse and OpenTelemetry wire formats. If you're already instrumented, migrate by changing a host — your existing code, spans, and exporters keep working.

Drop-in for the Langfuse Python and TypeScript SDKs.
Ingest OpenTelemetry spans through the standard OTLP endpoint.
No re-instrumentation — keep the trace code you already wrote.
Point your collector or SDK at Currai and ship.

↗Bring your SDK

Drop-in compatible 🔌

from langfuse import Langfuse

client = Langfuse(
    public_key="pk-lf-...",
    secret_key="sk-lf-...",
    host="https://www.currai.app",  # only this line changes
)

Use works with your stack in production

Byte-compatible with Langfuse SDKs and OpenTelemetry — point them at Currai and go. Currai keeps this information connected to the conversation, user, session, and supporting trace so product and engineering teams can investigate the same evidence.

Start with one production workflow, verify the captured data, and use the resulting evidence to find recurring friction, debug failures, and measure whether each release improves the agent experience.

Follow the Currai getting-started guide to connect a real agent, then review the AI agent monitoring playbook for a practical production workflow.

↗Get Started