dank/serverAppConfigs
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity
Files
b5211845dae8120a6872fedbfd469c0248c07cfc
serverAppConfigs/dankclaw/compose.yaml
T
Frank b5211845da Hermes: drop the :8090 healthcheck (messaging gateway has no HTTP endpoint) 
'hermes gateway run' starts the messaging gateway (Signal SSE), not the :8090
web dashboard, so probing 8090 always reported unhealthy. The container's
running state plus the daemon's SSE connection are the real health signal.
2026-08-20 12:30:42 -07:00

258 lines
8.3 KiB
YAML
Raw Blame History

# Dankclaw stack — AI, search, development & observability services.
# Deploy: cd /home/dank/serverAppConfigs && podman-compose -f dankclaw/compose.yaml up -d
# See ../docs/Dankclaw/ and ../docs/Infrastructure/ for service documentation.
services:
# --- SearXNG stack (gluetun + searxng + valkey) --------------------------
# These three services are now boot-persistent Quadlet units, not compose
# services. They live in searxng/quadlet/ and install to
# ~/.config/containers/systemd/ on the host. searxng reuses gluetun's netns
# (Network=gluetun.container) so its traffic exits the WireGuard tunnel.
# Deploy with: scripts/deploy-searxng-quadlet.sh dankclaw
# See ../docs/Dankclaw/SearXNG.md, Gluetun.md, Valkey.md.
# --- AI image generation (ROCm GPU backend, gfx1151) ---------------------
# Built from Containerfile.comfyui on AMD's gfx1151 torch base. The GPU is
# reached via the /dev/kfd + /dev/dri passthrough (checked host-side; the run
# user is already in the render group). Only the 'video' group is added:
# rootless podman cannot map the render gid into the container namespace.
# Models + data persist under /home/dank/comfyui-data. See ../docs/Dankclaw/ComfyUI.md.
comfyui:
build:
context: .
dockerfile: Containerfile.comfyui
image: comfyui-rocm:gfx1151
container_name: comfyui
restart: unless-stopped
command: ["python", "main.py", "--listen", "0.0.0.0", "--port", "8188"]
ports:
- "8188:8188"
devices:
- /dev/kfd:/dev/kfd
- /dev/dri:/dev/dri
group_add:
- video
volumes:
- /home/dank/comfyui-data/models:/opt/ComfyUI/models
- /home/dank/comfyui-data/input:/opt/ComfyUI/input
- /home/dank/comfyui-data/output:/opt/ComfyUI/output
- /home/dank/comfyui-data/custom_nodes:/opt/ComfyUI/custom_nodes
healthcheck:
test: ["CMD", "python3", "-c", "import urllib.request; urllib.request.urlopen('http://localhost:8188/')"]
interval: 30s
timeout: 10s
retries: 5
start_period: 180s
# --- Chat UI + agent -----------------------------------------------------
openwebui:
image: ghcr.io/open-webui/open-webui:main
container_name: openwebui
restart: unless-stopped
environment:
OPENAI_API_BASE_URL: "${OPENAI_API_BASE_URL}"
OPENAI_API_KEY: "${OPENAI_API_KEY}"
ports:
- "3000:8080"
volumes:
- /opt/openwebui/data:/app/backend/data
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8080/health"]
interval: 30s
timeout: 10s
retries: 3
hermes:
image: docker.io/nousresearch/hermes-agent:latest
container_name: hermes
restart: unless-stopped
# The image's default s6 entrypoint runs the interactive TUI, which exits
# without a TTY and crash-loops the container. Override it to run the
# headless gateway (the documented Docker mode). The gateway drops to the
# unprivileged hermes user (uid 10000), so the data dir must be writable by it.
entrypoint: ["bash", "-c", "hermes gateway run --force -v"]
environment:
HERMES_DATA_DIR: /data
# Point hermes's config/.env at the mounted data dir (persistent).
HERMES_HOME: /data
# Signal adapter -> the host signal-cli daemon. The container reaches the
# host via podman's host alias; 127.0.0.1 inside the container is not the host.
SIGNAL_HTTP_URL: "http://host.containers.internal:8080"
SIGNAL_ACCOUNT: "${SIGNAL_ACCOUNT}"
SIGNAL_ALLOWED_USERS: "${SIGNAL_ALLOWED_USERS}"
ports:
- "8090:8090"
volumes:
- /home/dank/hermes-data:/data
# No healthcheck: 'hermes gateway run' starts the messaging gateway (Signal
# SSE), not the :8090 web dashboard, so there is no HTTP endpoint to probe.
# The container's running state + the daemon's SSE connection are the signal.
# --- Git hosting (migrated from /opt/gitea) ------------------------------
postgres:
image: docker.io/library/postgres:16-alpine
container_name: gitea-postgres
restart: unless-stopped
environment:
POSTGRES_USER: gitea
POSTGRES_PASSWORD: "${GITEA_DB_PASSWORD}"
POSTGRES_DB: gitea
volumes:
- /opt/gitea/data/gitea-postgres:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U gitea"]
interval: 30s
timeout: 10s
retries: 3
gitea:
image: docker.io/gitea/gitea:latest
container_name: gitea-server
restart: unless-stopped
environment:
DATABASE_TYPE: postgres
DATABASE_HOST: gitea-postgres
DATABASE_NAME: gitea
DATABASE_USER: gitea
DATABASE_PASSWD: "${GITEA_DB_PASSWORD}"
DATABASE_PORT: "5432"
USER_UID: "1000"
USER_GID: "1000"
ports:
- "3001:3000"
- "2222:22"
volumes:
- /opt/gitea/data/gitea-gitea:/data
- /etc/timezone:/etc/timezone:ro
- /etc/localtime:/etc/localtime:ro
depends_on:
- postgres
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/"]
interval: 30s
timeout: 10s
retries: 3
# --- Observability -------------------------------------------------------
prometheus:
image: docker.io/prom/prometheus:latest
container_name: prometheus
restart: unless-stopped
command:
- --config.file=/etc/prometheus/prometheus.yml
- --storage.tsdb.path=/prometheus
- --storage.tsdb.retention.time=30d
- --web.enable-lifecycle
ports:
- "9090:9090"
volumes:
- /opt/prometheus/config:/etc/prometheus
- /opt/prometheus/data:/prometheus
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
interval: 30s
timeout: 10s
retries: 3
grafana:
image: docker.io/grafana/grafana:latest
container_name: grafana
restart: unless-stopped
environment:
GF_SERVER_ROOT_URL: "http://grafana.dankclaw.local"
GF_SECURITY_ADMIN_USER: "${GRAFANA_ADMIN_USER}"
GF_SECURITY_ADMIN_PASSWORD: "${GRAFANA_ADMIN_PASSWORD}"
ports:
- "3002:3000"
volumes:
- /opt/grafana/data:/var/lib/grafana
- /opt/grafana/provisioning:/etc/grafana/provisioning:ro
depends_on:
- prometheus
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
interval: 30s
timeout: 10s
retries: 3
loki:
image: docker.io/grafana/loki:latest
container_name: loki
restart: unless-stopped
command: ["-config.file=/etc/loki/loki-config.yaml"]
ports:
- "3100:3100"
volumes:
- /opt/loki/config:/etc/loki
- /opt/loki/data:/loki
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:3100/ready"]
interval: 30s
timeout: 10s
retries: 3
alloy:
image: docker.io/grafana/alloy:latest
container_name: alloy
restart: unless-stopped
volumes:
- /opt/alloy/config:/etc/alloy
- /run/systemd/journal/socket:/run/systemd/journal/socket:ro
- /var/log:/var/log:ro
- /var/lib/containers:/var/lib/containers:ro
depends_on:
- loki
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:12345/-/healthy"]
interval: 30s
timeout: 10s
retries: 3
node-exporter:
image: docker.io/prom/node-exporter:latest
container_name: node-exporter
restart: unless-stopped
network_mode: host
pid: host
volumes:
- /proc:/host/proc:ro
- /sys:/host/sys:ro
- /:/rootfs:ro
command:
- --path.procfs=/host/proc
- --path.sysfs=/host/sys
- --path.rootfs=/rootfs
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:9100/metrics"]
interval: 30s
timeout: 10s
retries: 3
# --- Reverse proxy + homepage -------------------------------------------
caddy:
image: docker.io/library/caddy:latest
container_name: caddy
restart: unless-stopped
ports:
- "80:80"
- "443:443"
volumes:
- ./Caddyfile:/etc/caddy/Caddyfile:ro
- /opt/caddy/data:/data
- /opt/caddy/config:/config
- ../shared/homepage:/srv/homepage:ro
depends_on:
- searxng
- comfyui
- openwebui
- hermes
- gitea
- grafana
- prometheus
- loki
healthcheck:
test: ["CMD", "wget", "--spider", "-q", "http://localhost:80/"]
interval: 30s
timeout: 10s
retries: 3
Reference in new issue View Git Blame Copy Permalink