Files
serverAppConfigs/serverAppConfigs-docs/index.md
T
Frank e133d2412d Merge origin/main into docs/radiance-prefill-decode-census
Two conflicts, both from the 2026-10-19 vault compaction on main:

* frontmatter description — main shortened it to satisfy OKF DESC
  (max 120 chars); this branch's longer wording would have failed the
  seam. Kept main's shape and folded the new §9 in by naming
  step-shape attribution instead of profiler attribution.
* the Related bullet for [[vLLM Porting and Compile Triage]] — that
  page was destroyed on main, so the link is dropped rather than
  resurrected; this branch's [[frank-archon]] row is kept.

Index rows regenerated with scripts/gen-vault-index.py.
2026-10-19 14:20:05 -07:00

13 KiB

serverAppConfigs — knowledge base

One fact, one owner. A page owns exactly one thing and everywhere else links to it with a wikilink. Shape, payload, eras, laws and rollback for an inference endpoint live on its endpoint page; scripts/<service>.env is the authority for every number, and a page that disagrees with it is the bug. Payload swaps are rows in an endpoint page's Eras table, never pages of their own. This index is a locator: one row, one clause, no numbers.

Inference endpoints

Page Owns
frank-archon The radiance endpoint: live shape and harness contract, every era with its rollback path, and the laws it taught.
frank-dragoon The iGPU endpoint: live shape, every era with its rollback path, the laws it paid for, and the files that own it.
frank-zealot The RTX 3090 endpoint: live shape exactly as the env ships it, every era with its rollback path, and its card laws.

Dankclaw services

Page Owns
ComfyUI ComfyUI is a node-based AI image generation engine.
ComfyUI Qwen-Image Workflows Proven Qwen-Image text-to-image workflows on Dankclaw: the recipes, the API call shape, and which models to add next.
Dankclaw Stack Service inventory and routing overview for the Dankclaw AI, development, and observability host.
Frank TTS The fleet's cloned-voice speech endpoint and the one voice surface consumers address; wired as the harness speech role.
Frank TTS Engine The engine behind the fleet's speech endpoint: its runtime, private bridge, and the surface it publishes.
Gitea Gitea deployment on Dankclaw with its web UI reverse-proxied by the canonical Caddy service.
Gluetun Gluetun is a lightweight VPN client container.
Hermes Hermes is the self-improving AI agent from Nous Research.
Hermes-Dashboard The Hermes web dashboard is a browser UI for managing the agent.
Hermes-WebUI The iPhone companion app for Hermes on Dankclaw and the ways it is reached from the LAN.
Marreta The content-cleaning proxy SearXNG borrows egress from: a quadlet pair in the VPN netns behind the guard chain.
Open Notebook The fleet's podcast generator: notes in, multi-speaker episode out, script and voices both served in-house.
OpenWebUI OpenWebUI is a self-hosted chat interface for LLMs.
Postgres PostgreSQL is the database backend for Gitea.
SearXNG SearXNG is a privacy-respecting metasearch engine.
SearXNG Providers How Google and other upstream search engines get blocked behind the Gluetun
Seerr The request manager for the *arr stack — the maintained successor to the archived Overseerr line.
Swap Configuration The host swapfile: why it is sized as it is, the resize ordering that avoids an OOM, and the swappiness caveat.
Valkey Valkey is the cache and limiter store for SearXNG.
Voice Packs How a voice pack is built: the files every pack must carry, the source-material gate, adding a voice, engine-bump drift.

Dankserver services

Page Owns
Calibre Calibre is the e-book library manager that backs Calibre-Web.
Calibre-Web Calibre-Web is a web application that browses, reads, and downloads eBooks from an existing Calibre library database.
Copyparty Copyparty is a lightweight file server and media streamer that runs as a single Python binary.
Dankserver Stack Service inventory and routing overview for the media and library host.
Entropy Volume The Dankserver entropy volume is a RAID-backed LUKS filesystem mounted at
Jellyfin Jellyfin on Dankserver: quadlet unit, entropy-volume data layout, ports, client access, hardware-transcode status.
mariadb The MariaDB backend for RomM: quadlet unit, network alias, env-file secret handling, and the backup path.
Plex Plex Media Server is a containerized media server on Dankserver: a podman
redis The Redis cache and task queue for RomM: quadlet unit, network alias topology, and the backup path.
RomM RomM (ROM Manager) is a self-hosted ROM library manager and player.
RomM-Scraping Metadata providers, cover art, ROM naming and the scraping workflow behind the RomM library.
Tautulli Tautulli is the statistics, monitoring, and notification companion for

FrankBook-Pro

Page Owns
ARR-Stack The *arr automation stack on FrankBook-Pro, every container on the VPN netns: topology, wiring, and gotchas.
lidarr Lidarr music manager in the *arr stack on FrankBook-Pro — live quadlet deployment, ports, volumes, and wiring facts.
prowlarr Indexer management for the *arr stack: feed routes, the sync model, the API surface, and verified live gotchas.
qbittorrent The download client for the *arr stack: pinned image, shared WireGuard netns, WebUI credential recipe.
radarr Radarr movie manager in the *arr stack on FrankBook-Pro — live quadlet deployment, ports, volumes, and wiring facts.
readarr The ebook and audiobook manager in the *arr stack: retired upstream, pinned image, parked download client.
sonarr Sonarr TV manager in the *arr stack on FrankBook-Pro — live quadlet deployment, ports, volumes, and wiring facts.

Workstations

Page Owns
Noctalia and Niri The noctalia shell on niri across workstations: config layers, remote IPC, custom palettes, output rotation and pinning.

Cross-host infrastructure

Page Owns
Alertmanager Receives firing rules from Prometheus, groups and dedupes them, and forwards each group to the host-side Signal relay.
Alloy Alloy is Grafana's log and telemetry shipper.
Anubis Anubis is the bot-challenge proxy that fronts the guarded public vhosts on
Authentik Authentik is the single sign-on (SSO) and OpenID Connect (OIDC) provider for the
Authentik Outpost Reference Outpost, proxy-provider, OAuth2, LDAP and flow configuration for the homelab's Authentik SSO.
Authentik Processes The three core Authentik containers — database, server and worker — with their units, images, roles and probes.
Caddy Caddy is the single reverse proxy for both hosts.
FrankBook-Pro FrankBook-Pro — the Mac mini running the *arr stack + qBittorrent inside a podman machine VM, gluetun-gated
Grafana Grafana visualizes the metrics that Prometheus collects from every service.
Homepage The password-protected service list on Dankclaw: what each card shows and where its data comes from.
Homepage Design Grilling The decision log for the homepage design.
Homepage Status Probes How probe targets are chosen, the three false-down shapes, the triage procedure, and the e2e gate interactions.
LAN-DNS The homelab gives every service a name under franksdank.cloud.
Loki Loki is the log aggregation backend of the observability stack.
Node-Exporter Node-Exporter exposes host metrics (CPU, RAM, disk, network) to Prometheus.
Observability The observability stack: what runs, how it is deployed, how it is exposed, and what is still unconfigured.
Observability Provisioning Monitoring config as code: the config triad, deploy copiers, planner mappings, and where each change type lands.
Pi-hole Pi-hole is the LAN DNS server for the homelab.
Prometheus Scrapes each service's metrics endpoint and feeds the provisioned Grafana datasource; down targets are structural.

Repo architecture and policy

Page Owns
Container Network Namespaces How Podman builds container networks here: the network inventory, the netns sharing mechanism, and the isolation limits.
Deploy State Triage Reading deploy-state markers against live containers and deciding, safely, whether to redeploy.
Deployment Flow Service-scoped Git deployment for the two homelab hosts.
E2E Suite The Playwright suite that drives the live fleet through a real browser, its project set, and the FrankBook conditional.
Network Architecture One Caddy fronts both hosts.
Quadlet Lifecycle The Quadlet discipline: ownership audits, compose cutover, drift and crash-loop triage, generator quirks, log retrieval.
Stale Signal Audit The audit battery for surfaces that rot without failing: dead probes, vacuous assertions, gates that never run.
Storage Policy All persistent data uses bind mounts: a host directory mapped directly into the container.
Testing Policy This repository tests its configuration at defined seams.

Operations and incidents

Page Owns
Container Host Reachability Two reachability quirks: containers cannot dial unpublished host ports, and netns membership decides reachability.
Fleet Audit and Posture Three standing audits: monitoring completeness, vhost proxy health, and behavioural security posture.
Fleet Ops Playbook Incident-shaped procedures: endpoint down with a GPU holder, stop-first bench windows, service iteration, waking a host.
Payload and Disk Reclaim Disk pressure procedure: measure every bucket, classify, prove nothing references the payload, stage, purge on approval.
Remote Job Runner Detached long jobs with sentinel files: why tail-watchers fail structurally, the script, its invariants, verification.
SSH and Remote Access Passwordless SSH bootstrap without sshpass, remote execution against fish login shells, and frozen-GUI triage.

Agent / harness

Page Owns
Agent Docs and Edits Two self-inflicted doc damage classes from parallel agent edits, with the audit checks and recovery order for each.
Command Center Dotfiles How the dotfiles repo deploys: stow-equivalent packages, full-replica rsync, the pre-overwrite audit, transport gotchas.
OMP Harness The omp harness as configured here: compaction chain arithmetic, per-model sampler routing, and the context-lean audits.

Research and methodology

Page Owns
AI Job Search and Resume Tools Self-hosted job-search and resume tools: the landscape, local-LLM fit, and the recommended homelab stack.
Backblaze Integration Off-site backup plan for the bind-mounted data on both hosts.
ComfyUI ROCm and Vulkan Whether ComfyUI can use the Strix Halo APU at all, and which backend path actually reaches the GPU.
PICO-8 Asset Standards Asset-sheet standards for PICO-8: palette discipline, one light direction, detail hierarchy, cohesion checklist.
Service Research Brief Consolidated upstream research on the fleet's LLM runtimes, dated to when it was gathered.

LLM technique and hardware references

Page Owns
Dankclaw Improvements This page collects concrete, sourced recommendations to improve Dankclaw
Dankclaw System Specs Dankclaw is an AMD APU server for CIRU ROCmFPX llama.cpp inference.
dankclaw-iommu-translation-off Why Dankclaw boots with identity DMA, what the earlier off-era bought and cost, and which tooling owns the boot line.
Dankserver System Specs Dankserver hardware and OS state since the board swap: board, lane topology, cards, memory, kernel posture.
DFlash DSpark Speculative Decoding DFlash and DSpark are the two newest speculative decoding methods.
GGUF Compatibility Answering whether an engine loads a GGUF from the file header alone, and pinning a fork build that can.
Heterogeneous Split Triage Triage before splitting across unequal accelerators: link characterisation, real bottleneck, what placement never buys.
Llama Cpp Serving Sizing Measurement-first sizing for llama.cpp shapes: slot pools against a headroom band, per-device accounting, prompt cache.
LLM Performance Diagnosis Probing why a served model is slow: the flat-depth probe, offload duty-cycle arithmetic, and step-shape attribution.
Model Swap and Rollback The model-swap discipline: fit preflight, fetch verification, build and flag checks, live validation, three-pin revert.
PCIe Link and Atomics Link probing, the streaming-versus-compute ceiling arithmetic, and the atomics wall that decides multi-GPU collectives.
Quantization by Hardware Architecture This page maps LLM quantization formats to the GPU and CPU architectures that support them.
Quantization Production Making a quantized payload here: the conversion recipe, the scoring gate, and the campaign ladder behind a shipped file.
RDNA4 MoE Expert Offload VRAM Budget Expert-offload arithmetic on the RDNA4 fork: movable terms, the utilisation law, graph charge, ceilings, context ladder.
Shared Memory Architecture Dankclaw Dankclaw uses AMD Strix Halo APU with unified memory architecture.