Deploy Arcnem Vision

Image analysis and agent workflows with OCR, search, and segmentation.

Deploy Arcnem Vision

Just deployed

/data

Just deployed

/var/lib/postgresql/data

Just deployed

/var/lib/postgresql/data

inngest-redis

redis:8.2

Just deployed

/data

Just deployed

Just deployed

Just deployed

Just deployed

vision-dashboard

arcnem-ai/arcnem-vision

Just deployed

Deploy and Host Arcnem Vision on Railway

Arcnem Vision is an open-source platform for image ingestion, analysis, and agent workflows. Upload images through the dashboard or API, build workflows for OCR, descriptions, embeddings, and segmentation, and inspect each run. The dashboard also supports similarity search, document chat, and AI-assisted workflow drafting.

About Hosting Arcnem Vision

This template deploys nine services: the API, dashboard, workflow agents, MCP analysis tools, PostgreSQL with pgvector, Redis, and a self-hosted Inngest server with its own PostgreSQL and Redis. The application services build from the Arcnem Vision repository using Dockerfiles. The API and dashboard have public Railway domains; internal services communicate over the private network. Database and Redis data use persistent volumes.

Bring an S3-compatible bucket, an OpenAI API key, and a Replicate API token. Fill in the required template variables, including the first owner's email and bucket credentials. The API runs migrations and production bootstrap before deployment, creating the first owner, organization, default project, and starter workflow.

After deployment, allow the dashboard's origin to make GET and PUT requests in your bucket's CORS policy. Open the dashboard and sign in with the owner email. By default, one-time sign-in codes appear in the API deployment logs. Before sharing project access, set AUTH_EMAIL_DELIVERY to resend and provide RESEND_API_KEY and TRANSACTIONAL_EMAIL_ADDRESS so codes are emailed. Public sign-up and organization creation are disabled by default.

Common Use Cases

  • Process uploaded images with OCR, descriptions, embeddings, and segmentation.
  • Build agent workflows with tool calls, routing, conditions, and persistent run history.
  • Search image collections, chat about documents, and integrate automated uploads through workflow API keys.

Dependencies for Arcnem Vision Hosting

Deployment Dependencies

  • An S3-compatible bucket with read/write credentials and a public base URL for documents you choose to publish. Cloudflare R2 is supported with region auto.
  • An OpenAI API key for descriptions, chat, and workflow drafting.
  • A Replicate API token for embeddings and segmentation.
  • Optionally, a Resend API key and sender address for emailed sign-in codes.

PostgreSQL, pgvector, Redis, and Inngest are included in this template. Railway hosting, external storage, and model-provider usage are billed by their respective providers.

Why Deploy Arcnem Vision on Railway

Railway keeps the application and supporting services in one project with private networking, persistent volumes, deployment logs, and public API and dashboard domains. The template connects the services, generates shared application secrets, and runs database preparation during API deployment.

See the deployment guide for bucket configuration and first sign-in. Source and documentation are available in arcnem-ai/arcnem-vision.


Template Content

inngest-redis

redis:8.2

vision-dashboard

arcnem-ai/arcnem-vision

More templates in this category

View Template
Chat Chat
Chat Chat, your own unified chat and search to AI platform.

okisdev
116
View Template
stella
Self-host stella with web, API, Postgres, Redis, and object storage.

Jan Kubica
7
View Template
Hermes Agent | OpenClaw Alternative with Dashboard
Self-Hosted Hermes AI Agent for Telegram, Discord & Slack

codestorm
82