← Templates · Monitoring & Analytics
LV
Langfuse v3 (core)
Community6 services
Langfuse, the open-source LLM observability platform — tracing, evals and prompt management for AI applications.
| Runs | 6 services |
|---|---|
| Stack | langfuse-weblangfuse-workerlangfuse-postgreslangfuse-clickhouselangfuse-redislangfuse-storage |
| Provisioned for it | Nothing, it's self-contained |
| Verified | Not yet |
Why deploy on Railyard
Railyard provisions all 6 services in this stack together — langfuse-web, langfuse-worker, langfuse-postgres, langfuse-clickhouse, langfuse-redis, langfuse-storage — wired to reach each other over the private network, on a server you already pay for.
Deploying Langfuse v3 (core) is one piece of a bigger stack you can keep building — add a database, a worker, a cache, or another app, all on the same servers you already pay for.
Good for
- LLM observability — tracing prompts, costs and latency
- Evaluating and debugging LLM app behavior in production
Good to know
- Postgres, ClickHouse, Redis and S3-compatible storage are all wired up automatically — storage runs SeaweedFS instead of MinIO since MinIO's own images are no longer pullable from Docker Hub, which is handled for you here
- Incoming trace events are persisted to storage first and the database second, so a brief database outage doesn't lose data — long-running upgrade migrations run as a background job instead of blocking the deploy