# ~$ selfhostedops — The €15/Month Self-Hosted Company Stack
# Series A · Episode 1 — https://youtube.com/@selfhostedops
#
# One server. One file. Your whole company stack:
#   caddy       reverse proxy + automatic HTTPS
#   forgejo     git hosting + CI (also acts as SSO/OIDC provider)
#   outline     team wiki (logs in via Forgejo SSO)
#   vaultwarden password manager (Bitwarden-compatible)
#   uptime-kuma monitoring + alerts
#   ntfy        push notifications for those alerts (episode 6)
#   n8n         automation hub
#   wg-easy     WireGuard VPN (optional — start with: --profile vpn)
#               (the full NetBird mesh is in netbird/ — episode 5)
#
# Quickstart:
#   1. cp .env.example .env   && edit it (domain, email, secrets)
#   2. Point *.${DOMAIN} (wildcard A/AAAA record) at this server
#   3. docker compose up -d
#
# Every image below is multi-arch (amd64 + arm64) — runs on a €14 ARM box.

name: selfhostedops-stack

networks:
  proxy:
    # Pinned on purpose. Compose hands the subnets out in creation order, so a
    # restore onto a fresh box can renumber them - and every NetBird route that
    # points at the old range stops working, silently (episode 8).
    ipam:
      config:
        - subnet: 172.18.0.0/16
    driver_opts:
      # Docker 28+ firewalls direct access to container IPs from other
      # interfaces (raw PREROUTING drop per container). This lets the NetBird
      # mesh interface reach the stack containers - see netbird/ (episode 5).
      com.docker.network.bridge.trusted_host_interfaces: "wt0"
  ci:
  internal:
    ipam:
      config:
        - subnet: 172.19.0.0/16

volumes:
  caddy_data:
  caddy_config:
  forgejo_data:
  outline_data:
  outline_pg:
  vaultwarden_data:
  kuma_data:
  ntfy_data:
  ntfy_cache:
  n8n_data:
  wg_data:
  docker_certs:
  dind_data:
  runner_data:

services:
  caddy:
    image: caddy:2-alpine
    restart: unless-stopped
    ports:
      - "80:80"
      - "443:443"
      - "443:443/udp"   # HTTP/3
    environment:
      DOMAIN: ${DOMAIN}
      ACME_EMAIL: ${ACME_EMAIL}
    volumes:
      - ./Caddyfile:/etc/caddy/Caddyfile:ro
      - caddy_data:/data
      - caddy_config:/config
    networks: [proxy]

  forgejo:
    image: codeberg.org/forgejo/forgejo:16
    restart: unless-stopped
    environment:
      USER_UID: "1000"
      USER_GID: "1000"
      FORGEJO__server__DOMAIN: git.${DOMAIN}
      FORGEJO__server__ROOT_URL: https://git.${DOMAIN}/
      FORGEJO__server__SSH_PORT: "2222"
      FORGEJO__service__DISABLE_REGISTRATION: "true"
      FORGEJO__openid__ENABLE_OPENID_SIGNIN: "false"
      FORGEJO__actions__ENABLED: "true"
      FORGEJO__repository__DEFAULT_REPO_UNITS: "repo.code,repo.issues,repo.pulls,repo.releases,repo.packages,repo.actions"
      # Forgejo refuses to deliver a webhook to a private address by default.
      # Calling the automation hub over the docker network is exactly that, so
      # the container name has to be listed. "external" keeps ordinary public
      # webhook targets working (episode 8).
      FORGEJO__webhook__ALLOWED_HOST_LIST: "external,n8n"
    ports:
      - "2222:22"       # git over SSH
    volumes:
      - forgejo_data:/data
    networks: [proxy]

  outline-postgres:
    image: postgres:16-alpine
    restart: unless-stopped
    environment:
      POSTGRES_USER: outline
      POSTGRES_PASSWORD: ${OUTLINE_PG_PASSWORD}
      POSTGRES_DB: outline
    volumes:
      - outline_pg:/var/lib/postgresql/data
    networks: [internal]

  outline-redis:
    image: redis:7-alpine
    restart: unless-stopped
    networks: [internal]

  outline:
    image: outlinewiki/outline:latest
    restart: unless-stopped
    depends_on: [outline-postgres, outline-redis]
    environment:
      URL: https://wiki.${DOMAIN}
      PORT: "3000"
      SECRET_KEY: ${OUTLINE_SECRET_KEY}
      UTILS_SECRET: ${OUTLINE_UTILS_SECRET}
      DATABASE_URL: postgres://outline:${OUTLINE_PG_PASSWORD}@outline-postgres:5432/outline
      PGSSLMODE: disable
      REDIS_URL: redis://outline-redis:6379
      FILE_STORAGE: local
      FILE_STORAGE_LOCAL_ROOT_DIR: /var/lib/outline/data
      FORCE_HTTPS: "false"   # TLS terminates at caddy
      # --- SSO via your own Forgejo (set up the OAuth2 app first, see README) ---
      OIDC_CLIENT_ID: ${OUTLINE_OIDC_CLIENT_ID}
      OIDC_CLIENT_SECRET: ${OUTLINE_OIDC_CLIENT_SECRET}
      OIDC_AUTH_URI: https://git.${DOMAIN}/login/oauth/authorize
      OIDC_TOKEN_URI: https://git.${DOMAIN}/login/oauth/access_token
      OIDC_USERINFO_URI: https://git.${DOMAIN}/login/oauth/userinfo
      OIDC_LOGOUT_URI: https://git.${DOMAIN}/logout
      OIDC_DISPLAY_NAME: Forgejo
      OIDC_SCOPES: openid profile email
    volumes:
      - outline_data:/var/lib/outline/data
    networks: [proxy, internal]

  vaultwarden:
    image: vaultwarden/server:latest
    restart: unless-stopped
    environment:
      DOMAIN: https://vault.${DOMAIN}
      ADMIN_TOKEN: ${VAULTWARDEN_ADMIN_TOKEN}
      SIGNUPS_ALLOWED: "${VAULTWARDEN_SIGNUPS_ALLOWED:-true}"  # set to false after your team joined!
      # --- Single sign-on via your own Forgejo (episode 4) ---
      # Create the OAuth2 app in Forgejo FIRST: Site Administration ->
      # Applications -> OAuth2. Its redirect URI must be exactly:
      #   https://vault.${DOMAIN}/identity/connect/oidc-signin
      # That path is not documented in the UI. Getting it wrong fails only
      # AFTER the Forgejo login, which is why it costs people twenty minutes.
      SSO_ENABLED: "true"
      # Just the base URL. Vaultwarden reads Forgejo's discovery document
      # (/.well-known/openid-configuration) from here on the first login.
      SSO_AUTHORITY: https://git.${DOMAIN}
      SSO_CLIENT_ID: ${VAULTWARDEN_SSO_CLIENT_ID}
      SSO_CLIENT_SECRET: ${VAULTWARDEN_SSO_CLIENT_SECRET}
      # Vaultwarden prepends "openid" itself, so listing it here again shows up
      # duplicated on the Forgejo consent screen. Harmless, but untidy.
      SSO_SCOPES: "profile email"
      # Attach an SSO login to the existing account with the same mail address
      # instead of creating a duplicate. Turn this on BEFORE people log in.
      SSO_SIGNUPS_MATCH_EMAIL: "true"
    volumes:
      - vaultwarden_data:/data
    networks: [proxy]

  uptime-kuma:
    image: louislam/uptime-kuma:1
    restart: unless-stopped
    volumes:
      - kuma_data:/app/data
    networks: [proxy]

  # Push notifications for the monitoring alerts (episode 6).
  # Uptime Kuma publishes to the topic "alerts", your phone subscribes to it.
  ntfy:
    image: binwiederhier/ntfy:v2.28.0
    restart: unless-stopped
    command: serve
    environment:
      NTFY_BASE_URL: https://ntfy.${DOMAIN}
      NTFY_BEHIND_PROXY: "true"
      NTFY_AUTH_DEFAULT_ACCESS: deny-all   # nobody reads or writes without a user
      NTFY_AUTH_FILE: /var/lib/ntfy/user.db
      NTFY_CACHE_FILE: /var/cache/ntfy/cache.db
      NTFY_ATTACHMENT_CACHE_DIR: /var/cache/ntfy/attachments
      NTFY_ENABLE_LOGIN: "true"
    volumes:
      - ntfy_data:/var/lib/ntfy
      - ntfy_cache:/var/cache/ntfy
    networks: [proxy]

  # The automation hub (episode 8). The editor stays on the mesh (episode 5);
  # Caddy publishes nothing but the webhook paths. Internal senders (forgejo,
  # uptime-kuma) call http://n8n:5678/webhook/... over the docker network and
  # never leave the box at all.
  n8n:
    # Pinned. With :latest every restore from backup is silently an upgrade,
    # and an upgrade is a thing you schedule, not a thing a restore does to you.
    image: docker.n8n.io/n8nio/n8n:2.37.7
    restart: unless-stopped
    environment:
      N8N_HOST: n8n.${DOMAIN}
      N8N_PORT: "5678"
      N8N_PROTOCOL: https
      # The address n8n prints under every webhook node. It must be the public
      # one, otherwise you hand your senders a URL that resolves nowhere.
      # (2.x renamed WEBHOOK_URL to this. The old name still works and prints a
      # deprecation line on every boot.)
      N8N_WEBHOOK_URL: https://n8n.${DOMAIN}/
      GENERIC_TIMEZONE: ${TZ:-Europe/Berlin}
      TZ: ${TZ:-Europe/Berlin}
      # The editor is opened over the mesh on plain http://<container-ip>:5678.
      # With secure cookies on, the browser never sends the session cookie back
      # and the login screen just reappears, with no error anywhere.
      N8N_SECURE_COOKIE: "false"
      # Do not let anyone install unverified community node packages here.
      # The default flips to false in a later version anyway.
      N8N_UNVERIFIED_PACKAGES_ENABLED: "false"
      # File nodes may read exactly one directory and nothing else. Left wide
      # open, a workflow could read /home/node/.n8n/config - the file that
      # decrypts every credential in the instance.
      N8N_RESTRICT_FILE_ACCESS_TO: /backup
      # Optional: pin the credential encryption key yourself instead of letting
      # n8n write one into the volume. See .env.example before you set this.
      N8N_ENCRYPTION_KEY: ${N8N_ENCRYPTION_KEY:-}
      # A company box does not need to phone home.
      N8N_DIAGNOSTICS_ENABLED: "false"
      N8N_VERSION_NOTIFICATIONS_ENABLED: "false"
      N8N_HIRING_BANNER_ENABLED: "false"
    volumes:
      - n8n_data:/home/node/.n8n
      # Read-only view of the nightly backup log (episode 7) so the digest
      # workflow can report the last restic snapshot. Optional: drop this line
      # and the digest says "no backup log found" instead of failing.
      - ./backup/backup.log:/backup/backup.log:ro
    networks: [proxy]

  # Optional starter VPN — enable with:  docker compose --profile vpn up -d
  # (The proper Netbird mesh deployment is Episode 5.)
  wg-easy:
    image: ghcr.io/wg-easy/wg-easy:14
    profiles: [vpn]
    restart: unless-stopped
    cap_add: [NET_ADMIN, SYS_MODULE]
    sysctls:
      net.ipv4.ip_forward: 1
      net.ipv4.conf.all.src_valid_mark: 1
    environment:
      WG_HOST: vpn.${DOMAIN}
      PASSWORD_HASH: ${WGEASY_PASSWORD_HASH}
    ports:
      - "51820:51820/udp"
    volumes:
      - wg_data:/etc/wireguard
    networks: [proxy]


  # The only thing in this stack that is allowed to change state (episode 9).
  # The agent never talks to it. n8n does, and only after a switch node has
  # matched the model's proposed action against a fixed list. This service
  # checks the same thing again, plus a second list of containers it may
  # touch at all. Two locks on one door cost nothing.
  #
  # Start it with:  docker compose --profile agent up -d
  ops-actions:
    image: docker:cli
    profiles: [agent]
    restart: unless-stopped
    environment:
      OPS_ACTIONS_TOKEN: ${OPS_ACTIONS_TOKEN}
    volumes:
      - ./ops-actions/runner.py:/runner.py:ro
      # Yes, this is the docker socket. That is exactly why the allowlists are
      # inside this container and not in a workflow anyone can edit.
      - /var/run/docker.sock:/var/run/docker.sock
    entrypoint: ["sh", "-c"]
    command: ["apk add --no-cache python3 >/dev/null && exec python3 -u /runner.py"]
    networks: [proxy]

  # --- CI (episode 2) -- start with: docker compose --profile ci up -d ---

  docker-in-docker:
    image: data.forgejo.org/oci/docker:dind
    # The hostname MUST be "docker": the TLS certificates dind generates are
    # only valid for that name. Rename it and you get a handshake error that
    # reads like a network problem and is not one.
    hostname: docker
    profiles: [ci]
    privileged: true
    restart: unless-stopped
    environment:
      DOCKER_TLS_CERTDIR: /certs
    volumes:
      - docker_certs:/certs
      - dind_data:/var/lib/docker
    networks: [ci]

  forgejo-runner:
    image: data.forgejo.org/forgejo/runner:13.0.0
    profiles: [ci]
    restart: unless-stopped
    depends_on: [docker-in-docker]
    environment:
      DOCKER_HOST: tcp://docker:2376
      DOCKER_CERT_PATH: /certs/client
      DOCKER_TLS_VERIFY: "1"
    volumes:
      - runner_data:/data
      - docker_certs:/certs
      - ./runner-config.yml:/data/config.yml:ro
    networks: [ci, proxy]
    command: forgejo-runner --config /data/config.yml daemon