Langfuse

Deploy Langfuse on your own Kubernetes cluster with Edka’s one click installation. Langfuse traces LLM calls, manages prompts, runs evaluations, and stores datasets, while the data plane stays inside your cluster.

What Edka Provisions

Edka installs Langfuse from the Edka Helm chart and wires it into the managed services already running in your cluster:

• Langfuse web and worker: Separate deployments for the UI/API and background jobs, with independent replica and resource settings.
• PostgreSQL metadata store: Select an existing managed PostgreSQL installation, database, and user for Langfuse application data.
• ClickHouse event store: Select an existing managed ClickHouse installation and a dedicated database for high-volume traces and events.
• Valkey queue and cache: Attach an existing managed Valkey installation.
• S3-compatible object storage: Select an organization object storage integration for event upload, batch export, and media upload storage.
• Gateway access: Optionally expose the Langfuse UI and API through a cluster traffic class and hostname.

Configuration Options

• Datastores: Choose the PostgreSQL, ClickHouse, and Valkey instances Langfuse should use. Edka resolves credentials from Kubernetes Secrets and projects them into the Langfuse runtime secret.
• Object storage: Choose an S3-compatible integration for Langfuse event, export, and media buckets.
• Security: Edka generates a stable salt, session secret, and 64-character hexadecimal encryption key for Langfuse. You can also provide an optional Enterprise license key.
• Authentication: Disable public signups, disable username/password auth, or keep the default first-run setup flow.
• Resources: Tune web and worker replicas, CPU and memory requests, memory limits, and Node.js runtime options.
• Auto-updates: Optionally let the Edka agent apply newer chart and image versions automatically using a patch, minor, major, or custom policy.

Agent Tracing

Hermes Agent can send traces to an installed Langfuse instance. Enable tracing in the Hermes configuration, select the Langfuse instance in the same cluster, and provide the project public and secret keys. Edka fills the in-cluster base URL from the selected instance, so Hermes reaches Langfuse over the cluster service, not a public route.

Getting Started

1. Click “Deploy Langfuse” below.
2. Select existing PostgreSQL, ClickHouse, and Valkey instances.
3. Select an S3-compatible object storage integration.
4. Choose whether to expose Langfuse through a Gateway traffic class.
5. Deploy, open Langfuse, create a project, and copy the project keys into your agent or application configuration.

Deploy Langfuse