Replace the dead dankserver open-webui (bare container, :3000, pointed at a dead :9090 backend) with a boot-persistent quadlet on dankclaw: - CPU image (:main); dankclaw is CPU-only, so the :cuda image is wasted. - Isolated on slirp4netns; publishes 3005 (3000 is Gitea's HTTP port). - Default LLM backend is the local vLLM on 52625 (frank-default-large). - Data persists under /home/dank/Containers/open-webui/data. - Caddy route now proxies to the published LAN port (the container is not on Caddy's network). Also corrects the model/port mapping in the docs: the live state (verified 2026-08-19) is frank-default-large on vLLM :52625 (dankclaw) and frank-default-small on llama.cpp :7770 (dankserver) — the reverse of the 2026-08-17 note.
2.6 KiB
Dankclaw Stack
Dankclaw (192.168.0.143) runs the AI, search, and development stack. It
hosts the vLLM inference endpoint (frank-default-large, :52625, from
the vllmScripts repo), the agent tools, the privacy search, and the
observability stack. The llama.cpp endpoint (frank-default-small,
:7770) runs on Dankserver (192.168.0.235).
graph LR
U[User] --> C[Caddy :80/:443]
C --> O[OpenWebUI]
C --> S[SearXNG]
C --> G[Gitea]
C --> F[ComfyUI]
C --> D[Grafana]
S --> V[Gluetun VPN]
O --> L[llama.cpp dankserver :7770]
O --> H[Hermes]
O --> E[vLLM dankclaw :52625]
Services
| Service | Hostname | Port | Docs |
|---|---|---|---|
| SearXNG | search.dankclaw.local | 8081 | SearXNG |
| ComfyUI | comfyui.dankclaw.local | 8188 | ComfyUI |
| OpenWebUI | chat.dankclaw.local | 3005 | OpenWebUI |
| Hermes | hermes.dankclaw.local | 8090 | Hermes |
| Gitea | gitea.dankclaw.local | 3000 | Gitea |
| Grafana | grafana.dankclaw.local | 3002 | Grafana |
| Prometheus | prometheus.dankclaw.local | 9090 | Prometheus |
| Homepage | dankclaw.local | 80/443 | — |
| frank-default-large (host service, Dankclaw) | — | 52625 | vllmScripts |
| frank-default-small (host service, Dankserver) | — | 7770 | vllmScripts |
The last two rows are bare-metal systemd services, not containers. The
vllmScripts repository owns their scripts and knowledge base. The live
mapping (verified 2026-08-19) is the reverse of the 2026-08-17 note:
frank-default-large runs vLLM on Dankclaw; frank-default-small runs
llama.cpp FastMTP on Dankserver.
Boot Persistence
The Gitea trio, the SearXNG trio (gluetun, searxng, valkey), and open-webui run as quadlet units, so they start at boot. User linger is on. ComfyUI runs as a systemd unit around a bare process. The remaining services in the table are defined in compose.yaml and are not yet boot-persistent.
Deploy the SearXNG trio with scripts/deploy-searxng-quadlet.sh dankclaw and open-webui with scripts/deploy-open-webui-quadlet.sh dankclaw. The Gitea units install to ~/.config/containers/systemd/ (see Gitea).
Routing Rules
- SearXNG outbound traffic exits through the Gluetun VPN container.
- Every other service uses the normal LAN route.
- The homepage lists all services with status.
See Also
- index — repository index
- Network Architecture — routing and proxy
- Observability — Grafana, Prometheus, logs
- vllmScripts knowledge base — the model-serving endpoints on this host