Langfuse on Railway

Open-source LLM observability: traces, evaluations and prompt management, self-hosted on Railway.

Official site · License: MIT (ee directories under the Langfuse enterprise licence) · 21 Railway templates

Deploy Langfuse on RailwayCompare templates

Langfuse is an open-source platform for observing LLM applications. It collects traces of model calls and agent runs, tracks cost and latency, supports evaluations and datasets, and manages prompt versions. It is often compared with LangSmith and Helicone, with the difference that you can run it on your own infrastructure.

Teams self-host Langfuse to keep prompts and model outputs in their own environment. Version 4 stores traces in ClickHouse, application data in Postgres, queues in Redis and raw events in S3-compatible storage, and accepts data through its SDKs or OpenTelemetry.

The Langfuse core is MIT-licensed. Code in its ee directories uses the Langfuse enterprise licence.

What Langfuse can do

  • Tracing for LLM calls and agent runs
  • Cost and latency tracking
  • Evaluations, datasets and experiments
  • Prompt management with versions
  • OpenTelemetry endpoint for SDKs and exporters
  • Projects, organisations and API keys

What people use it for

  • Debugging and tracing an LLM application or agent
  • Tracking token cost across models and users
  • Versioning and testing prompts
  • Running evaluations on production traces

Videos

10 min Walkthrough of Langfuse – Open Source LLM Observability, Evaluation, and Prompt Management · Langfuse
Get Started with Langfuse - Open-Source LLM Monitoring · Dave Ebbelaar
Langfuse Walkthrough - Full Demo of Agent Tracing, Evals, Experiments and Prompt Management · Langfuse

Running Langfuse on Railway

The Railway template deploys the full Langfuse v4 stack: the web app and a background worker pinned to 4.56.0, ClickHouse, Postgres, Redis and a Railway Bucket for raw events, media and exports. The first admin, organisation, project and API keys are created on first start and public sign-up is disabled. Cost follows memory across the five services plus volumes and bucket storage; the web service needs at least 1.5 GB, and ClickHouse is the other main consumer as ingestion grows.

Langfuse templates on Railway

Langfuse v4 LLM Observability StackMaintained by Tracklayer
Deploys the full Langfuse v4 stack for tracing, evaluating and cost-tracking LLM applications: web app, background worker, ClickHouse, Postgres, Redis and a Railway Bucket. It suit
2 deployments
Deploy
Langfuse v3 by Langfuse's Projects
Open source observability and analytics for LLM applications
688 deployments
Deploy
Langfuse v2 by an independent creator
Open source observability and analytics for LLM applications
209 deployments
Deploy
Langfuse v3.227.1 (Production ready AI Observability) by an independent creator
Open-source LLM platform for prompt management, tracing, evals & metrics
44 deployments
Deploy
Langfuse | Open Source LangSmith Alternative for LLM Observability by an independent creator
Self-hosted LLM tracing, prompt management and evaluations
36 deployments
Deploy
Langfuse by an independent creator
Langfuse v4 Pro Stack LLM observability. Langfuse ClickHouse/S3. Lang Fuse.
15 deployments
Deploy
Agentic Data Stack Lite (Langfuse Cloud) by an independent creator
The Agentic Data Stack instrumented with Langfuse Cloud
14 deployments
Deploy
Langfuse | Open Source LLM Observability (DataDog Alternative) by an independent creator
Self Host Langfuse on Railway. Traces, Evals & Prompt Management
14 deployments
Deploy
Langfuse v4 by an independent creator
Self-host Langfuse on Railway: LLM tracing, evals and prompt management
11 deployments
Deploy
Langfuse v4.78.0 (Production ready AI Observability) by an independent creator
Open-source LLM platform for prompt management, tracing, evals & metrics
8 deployments
Deploy
Langfuse Observability Stack by an independent creator
Langfuse LLM tracing with ClickHouse, Postgres, Redis and MinIO
7 deployments
Deploy
Langfuse by an independent creator
Langfuse v4 with ClickHouse, S3 bucket and API keys ready on first boot
4 deployments
Deploy
Langfuse by an independent creator
A platform for LLM observability, tracing, evaluation, & prompt management.
4 deployments
Deploy
Langfuse v3 by an independent creator
Self-hosted LLM observability: tracing, evals & prompt management
3 deployments
Deploy
Langfuse by an independent creator
Langfuse v4: LLM tracing, evals and prompts, admin and keys set at deploy
2 deployments
Deploy
Langfuse Lite (Auto-Updated) by an independent creator
Just 3 services + a bucket instead of 6. Pre-prod LLM observability.
1 deployments
Deploy
Langfuse v4 by an independent creator
Self-host Langfuse v4 with ClickHouse, Redis and S3 storage.
1 deployments
Deploy
Langfuse v4 by an independent creator
Langfuse v4 LLM observability, ready on first login, sign-up closed
1 deployments
Deploy
AI Gateway + Observability (LiteLLM × Langfuse) by an independent creator
[Sep'26] LiteLLM gateway + Langfuse tracing, pre-wired. 100+ LLMs
0 deployments
Deploy
Deploy Langfuse Datasets and Experiments by an independent creator
Versioned test sets and experiment runs for LLM apps
0 deployments
Deploy
Langfuse by an independent creator
Trace, evaluate and debug LLM apps and agents on your own Langfuse.
0 deployments
Deploy

Tracklayer templates are listed first. Other Langfuse templates follow, ordered by total deployments on Railway. How this works.

Deployment numbers as of 2026-11-20.

Questions about Langfuse

How do I log in?

Enter your email in LANGFUSE_INIT_USER_EMAIL when deploying. After langfuse-web is healthy, which can take several minutes on first start while migrations run, sign in with that email and the generated LANGFUSE_INIT_USER_PASSWORD from the langfuse-web variables, then change the password.

Which Railway plan do I need?

Hobby or Pro. langfuse-web needs at least 1.5 GB of memory, so Trial (1 GB per service) and Free (0.5 GB) cannot run it; it stops with a JavaScript heap out of memory error.

Is my data kept across redeploys?

Yes. ClickHouse, Postgres and Redis each use a volume, and raw events, media and exports go to the Railway Bucket.

How do I upgrade?

Web and worker are pinned to the same version and must be upgraded together. Change the image tag in the web Dockerfile and on the worker, check the Langfuse changelog and redeploy. Migrations run when the web service starts.

What is the licence?

The core is MIT. Code under the ee directories uses the Langfuse enterprise licence and is not enabled by this template. ClickHouse is Apache-2.0.

Guides

Similar apps

Tracklayer maintains the templates marked as such; Langfuse is a trademark of its owners and this site is not affiliated with them.