Railway

Deploy Langfuse v3

Self-hosted LLM observability: tracing, evals & prompt management

Deploy Langfuse v3

Just deployed

/var/lib/clickhouse

postgres

postgres:17

Just deployed

/var/lib/postgresql

Just deployed

/data

Just deployed

Deploy and Host Langfuse

Deploy on Railway

Langfuse is an open-source LLM observability platform — the self-hosted alternative to LangSmith. It gives you tracing, metrics, evals, and prompt management for your LLM applications in one place.

About Hosting

This template deploys the production Langfuse v3 stack on Railway as a 6-service application:

ServicePurpose
langfuse-webNext.js app server (frontend + API), port 3000
langfuse-workerBackground job processor
postgresPrimary database (postgres:17 with pgvector)
clickhouseAnalytics database for event traces
redisCache + BullMQ job queue
minioS3-compatible object storage for media and batch exports

Why Deploy

  • One-click setup — every credential (Postgres, Redis, ClickHouse, MinIO, encryption keys) is auto-generated on first deploy.
  • Zero config — services are wired together with Railway companion references; no manual URL or password plumbing.
  • Production-shaped — persistent volumes on all stateful services, so your data survives redeploys.
  • Cost-effective — a full LLM observability stack for roughly $8.50/mo on Railway's Hobby plan.

Common Use Cases

  • Tracing and debugging LLM agent/production calls (OpenAI, Anthropic, and any Langfuse SDK).
  • Building evaluation pipelines over real production traces.
  • Prompt versioning and management.
  • Self-hosting your observability data instead of sending it to a SaaS vendor.

Dependencies

This template provisions its own Postgres, ClickHouse, Redis, and MinIO — no external services required.

Dependencies for

This template provisions all of its backing services itself — deployed together as a single project.

Deployment Dependencies

  • Postgres — provisioned in-project (persistent volume at /var/lib/postgresql/data)
  • ClickHouse — provisioned in-project (persistent volume at /var/lib/clickhouse)
  • Redis — provisioned in-project (persistent volume at /data)
  • MinIO — provisioned in-project (persistent volume at /data)

No external databases, queues, or storage are required.

Configuration

All environment variables are managed by Railway. On first deploy:

  1. ENCRYPTION_KEY is auto-generated (64-char hex)
  2. NEXTAUTH_SECRET and SALT are auto-generated
  3. Database credentials are auto-generated per service
  4. Redis password is auto-generated

After Deploy

  1. Open the web app at your Railway public domain.
  2. Create your first organization and project.
  3. Use the generated API keys to integrate Langfuse with your LLM applications.

Storage

  • Postgres: Persistent volume at /var/lib/postgresql/data
  • ClickHouse: Persistent volume at /var/lib/clickhouse
  • Redis: Persistent volume at /data
  • MinIO: Persistent volume at /data

Resource Estimates

ServiceMemoryCost/mo
langfuse-web512 MB~$2
langfuse-worker512 MB~$2
postgres256 MB~$1
clickhouse512 MB~$2
redis128 MB~$0.50
minio256 MB~$1
Total~2.2 GB~$8.50

Updating

To update Langfuse, redeploy with the new image tag. Database migrations run automatically on startup.

License

Langfuse is MIT-licensed. See https://github.com/langfuse/langfuse for details.


Template Content

More templates in this category

View Template
Pyroscope profiling
Protected continuous profiling with durable Pyroscope storage.

Anton Orel
1
View Template
SigOnly
Deploy SigNoz with a working demo app & config in one click

zoeyjones
22
View Template
Unwrapped Spotify Music Stats
Unwrapped Spotify Music Stats, Estatísticas de músicas disponíveis

Jorge Henrique
1