--- title: "Deploy Alquimia Stack" description: "Deploy Alquimia Stack on Railway" category: "AI/ML" url: https://railway.com/deploy/alquimia-stack-2 --- # Deploy Alquimia Stack Deploy Alquimia Stack on Railway **[Deploy Alquimia Stack on Railway](https://railway.com/template/alquimia-stack-2)** - **Creator:** Alquimia Projects - **Category:** AI/ML - **Total deploys:** 49 ## Template content ### minio-init https://cdn.simpleicons.org/minio/white - **Image:** minio/mc:latest - **Start command:** `sh -lc 'until mc alias set minio http://minio.railway.internal:9000 "$MINIO_ROOT_USER" "$MINIO_ROOT_PASSWORD"; do sleep 2; done; mc mb --ignore-existing minio/alquimia'` ### redis https://cdn.simpleicons.org/redis/white - **Image:** redis:7 ### oras-registry https://cdn.simpleicons.org/opencontainersinitiative/white - **Image:** ghcr.io/oras-project/registry ### runtime-postgres https://cdn.simpleicons.org/postgresql/white - **Image:** postgres:latest ### kafka - **Image:** redpandadata/redpanda:latest - **Start command:** `/usr/bin/rpk redpanda start --mode dev-container --smp 1 --memory 512M --overprovisioned --node-id 0 --check=false --kafka-addr 0.0.0.0:9092 --advertise-kafka-addr kafka.railway.internal:9092` ### prometheus - **Image:** alquimiaai/prometheus:railway-v2 - **Health check:** /-/ready - **Public domain:** Yes ### vault https://cdn.simpleicons.org/vault/white - **Image:** alquimiaai/vault-railway:20260529 - **Start command:** `sh -lc 'vault server -dev -dev-listen-address=0.0.0.0:8200 -dev-root-token-id="$VAULT_DEV_ROOT_TOKEN_ID"'` - **Health check:** /v1/sys/health ### trustlens - **Image:** alquimiaai/trustlens:stable-20260714-1613 - **Health check:** /health/readiness ### studio https://docs.alquimia.ai/favicon.ico - **Image:** alquimiaai/studio:latest-20260714-2037 - **Health check:** / - **Public domain:** Yes ### runtime https://docs.alquimia.ai/favicon.ico - **Image:** alquimiaai/runtime:dev - **Start command:** `sh -lc 'mkdir -p /data "$DOCKER_CONFIG" && printf "%s\n" "provider_id: inmemory" "params: {}" > /data/embeddings.yaml && AUTH="$(printf "%s:%s" "$REGISTRY_PROXY_USERNAME" "$REGISTRY_PROXY_PASSWORD" | base64 | tr -d "\n")" && printf "{\"auths\":{\"%s\":{\"username\":\"%s\",\"password\":\"%s\",\"auth\":\"%s\"}}}\n" "$REGISTRY_PROXY_HOST" "$REGISTRY_PROXY_USERNAME" "$REGISTRY_PROXY_PASSWORD" "$AUTH" > "$DOCKER_CONFIG/config.json" && chmod 600 "$DOCKER_CONFIG/config.json" && exec uv run --no-sync python src/main.py'` - **Health check:** /health/liveness - **Public domain:** Yes ### qdrant https://cdn.simpleicons.org/qdrant/white - **Image:** qdrant/qdrant:latest ### minio https://cdn.simpleicons.org/minio/white - **Image:** quay.io/minio/minio:latest - **Start command:** `minio server --console-address :9001 /data` ### trustlens-postgres https://devicons.railway.app/i/postgresql.svg - **Image:** ghcr.io/railwayapp-templates/postgres-ssl:18 ## Documentation # Deploy and Host Alquimia Stack on Railway Alquimia Stack is an AI agent runtime and builder environment for creating, configuring, and testing AI agents. It includes Alquimia Studio, Runtime, Router, registry storage, secrets support, vector search, object storage, and the supporting infrastructure needed to run a complete agent workflow on Railway. ## About Hosting Alquimia Stack Hosting Alquimia Stack on Railway deploys the core services required to run the Studio-based agent workflow end to end. The template provisions the web app, runtime API, router, Postgres, Redis, Qdrant, MinIO, Vault, and ORAS registry using Railway private networking. After deployment, users only need to provide required secrets and configure Lite authentication users in the Studio service. This setup is intended for demos, internal testing, customer trials, and lightweight production-like environments where a fast, reproducible deployment is more important than managing infrastructure manually. ## Why Deploy 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 Alquimia Stack 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. ## Common Use Cases - Quickly deploy Alquimia Studio to create, configure, and test AI agents. - Run customer demos or internal trials with a reproducible Railway environment. - Validate Runtime, registry, secrets, vector storage, and object storage integrations without manually wiring infrastructure. ## Dependencies for Alquimia Stack Hosting - A Railway account with access to deploy templates. - Alquimia Docker images and registry credentials configured in the template. - Lite authentication users configured through the `AUTH_LITE_USERS` variable in the `studio` service after deployment. - External LLM/model provider credentials, depending on the models you configure inside Studio. ### Deployment Dependencies - Railway Templates: https://docs.railway.com/templates - Railway Private Networking: https://docs.railway.com/private-networking - Railway Variables: https://docs.railway.com/variables - Alquimia Docker Hub organization: https://hub.docker.com/u/alquimiaai ### Implementation Details After deploying the template, set the `AUTH_LITE_USERS` variable in the `studio` service. Example value: ```env AUTH_LITE_USERS='[{"email":"admin@alquimia.ai","name":"Alquimia Admin","password_hash":""}]' ## Similar templates - [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform. - [stella](https://railway.com/deploy/stella) — Self-host stella with web, API, Postgres, Redis, and object storage. - [Hermes Agent | OpenClaw Alternative with Dashboard](https://railway.com/deploy/hermes-agent-or-openclaw-alternative-wit) — Self-Hosted Hermes AI Agent for Telegram, Discord & Slack Open this page in a browser: https://railway.com/deploy/alquimia-stack-2