ClickStack

ClickStack brings logs, metrics, and traces together for operational monitoring. Langfuse adds workflows for inspecting AI execution, evaluating outputs, improving prompts, and turning production examples into experiments. Both support OpenTelemetry, so you can send the same traces to both destinations.

Why use both?

A slow or unsuccessful agent request raises different questions. An operations engineer might look for a failing dependency or SLO breach. An AI engineer might inspect the prompt, retrieved context, and tool calls. Shared trace context lets both teams investigate the same request in the tool they already use.

Langfuse connects production observations to a continuous improvement loop. ClickStack overlaps with the Observe and Monitor stages for operational work.

flowchart LR
    subgraph langfuse_loop["Langfuse: continuous AI improvement"]
        direction LR
        subgraph operational_overlap["Overlap with ClickStack: operational use cases"]
            direction LR
            observe["Observe"] --> monitor["Monitor"]
        end
        monitor --> datasets["Datasets"]
        datasets --> experiments["Experiments"]
        experiments --> prompts["Prompt management"]
        prompts --> observe
    end

    classDef loopBox fill:none,stroke:#888,stroke-width:2px
    classDef overlapBox fill:none,stroke:#ea580c,stroke-width:2px,stroke-dasharray:5 5
    class langfuse_loop loopBox
    class operational_overlap overlapBox

Each team can set its own sampling and retention. An AI team may keep a broad history for evaluation; an operations team may keep what it needs for incidents. Neither product requires a particular split.

Anthropic and OpenAI use ClickHouse for observability at scale.

Recommended integration: export to both destinations

Instrument your application with OpenTelemetry and export to a Langfuse project and your ClickStack environment.

flowchart LR
    app["Your application / AI agent"] --> otel["OpenTelemetry instrumentation"]
    otel -->|"Export traces"| obs["ClickStack"]
    otel -->|"Export traces"| langfuse["Langfuse"]
    obs --> ops["Operational monitoring and incident investigation"]
    langfuse --> improve["Evaluation and continuous AI improvement"]

Export from the application or through an OpenTelemetry Collector. Keep the original trace context on both paths so the same request is identifiable in each tool. Apply destination-specific sampling after the paths split if you need different coverage.

• Langfuse: OpenTelemetry integration for the ingestion endpoint and supported instrumentation. Include AI-specific attributes such as model inputs and outputs.
• ClickStack: OpenTelemetry ingestion and the ingestion overview.
• Shared trace context: Trace IDs and distributed tracing.

Send a test request and confirm the same trace ID appears in both tools. Logs and metrics can continue to flow to ClickStack.

Open source

ClickStack is open source. It combines ClickHouse, OpenTelemetry, and the HyperDX interface.

Monitor self-hosted Langfuse with ClickStack

If you self-host Langfuse, you can also send stdout logs from langfuse-web and langfuse-worker to ClickStack. A node agent tails the container log files and a ClickStack collector writes them to a dedicated ClickHouse Cloud service, separate from CLICKHOUSE_URL. See Export self-hosted Langfuse logs to ClickStack for the Helm values, collector setup, and Logs source.

Roadmap

We are working on deeper cross-linking and shared instrumentation so you can move between the two workflows without duplicating data.

Questions? Contact support or open a GitHub issue.