Deploy and Host Label Studio on Railway

Label Studio is an open-source data labeling tool for machine learning. Teams annotate text, images, audio, video and time series with configurable interfaces for classification, named entities, bounding boxes, segmentation and LLM evaluation. It exports to common formats and connects to model backends for pre-labeling and active learning through its API and Python SDK.

About Hosting Label Studio

This template deploys Label Studio v1.23.0 from the official image with a Railway Postgres database. Uploaded files and media live on a Railway volume, so they survive redeploys. The admin account is created from environment variables on first start, and sign-up without an invite link is disabled. CSRF and host settings point at your Railway domain, so login works behind Railway's HTTPS proxy. For API access, create a personal access token in the account settings. It fits the Hobby plan for small projects. Back up Postgres and the volume regularly.

Common Use Cases

Labeling training data for text, vision and audio models
Evaluating and ranking LLM outputs with human reviewers
Reviewing model predictions and correcting them before retraining

Dependencies for Label Studio Hosting

heartexlabs/label-studio:1.23.0 (official image)
Railway Postgres (ghcr.io/railwayapp-templates/postgres-ssl:18) with a volume
A Railway volume at /label-studio/data

Deployment Dependencies

Implementation Details

Service	Image	Networking	Storage
labelstudio	`heartexlabs/label-studio:1.23.0`	public domain on 8080	volume at `/label-studio/data`
Postgres	Railway Postgres 18	private only	volume

from label_studio_sdk import LabelStudio
ls = LabelStudio(base_url="https://", api_key="")
print([p.title for p in ls.projects.list()])

Variable	Default	Purpose
`LABEL_STUDIO_USERNAME` / `LABEL_STUDIO_PASSWORD`	`admin@example.com` / generated	Admin account, created on first start
`LABEL_STUDIO_DISABLE_SIGNUP_WITHOUT_LINK`	`true`	Only invited users can sign up
`LABEL_STUDIO_HOST` / `CSRF_TRUSTED_ORIGINS`	`https://`	Public URL

Notes:

Legacy API tokens are disabled by default in 1.23; use personal access tokens.
The service runs as root (RAILWAY_RUN_UID=0) so it can write to the volume.

This is a community-maintained deployment package and does not imply affiliation with or endorsement by the Label Studio project or its maintainers.

Why Deploy Label Studio on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Label Studio on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.