LLM-maintained knowledge base for ps1raf
Find a file
raf 0d318991e2 task 29: pull crit-vuln images + recheck (143->103 crit on updated set)
🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 08:31:00 +02:00
conventions docs(audio-player): TLS via nginx at https://ps1raf:5055/ (loop task 262) 2026-05-17 08:44:27 +02:00
corrections openvas: root-cause + fix weekly-diff rc=1 (empty-report PDF abort) 2026-06-07 17:35:12 +02:00
external external: ubiquiti mFi revival research (loop task 163) 2026-04-25 07:50:40 +02:00
infrastructure host: document 2026-06-08 footprint reduction (67->27 containers) 2026-06-08 12:28:06 +02:00
lessons lessons: dhcpcd strips tailscale DNS — fix via /etc/resolv.conf.head 2026-04-29 22:46:13 +02:00
services task 34: stop stalwart (re-disabled quadlet) 2026-06-21 20:34:03 +02:00
tools loop-archive: daily loop.md trim (keep last 25, archive older finished) 2026-06-09 11:44:47 +02:00
CHANGELOG.md task 29: pull crit-vuln images + recheck (143->103 crit on updated set) 2026-06-22 08:31:00 +02:00
index.md claude-carbon: mark REMOVED (carbon report removed entirely) 2026-06-07 19:00:12 +02:00
LLMWIKI.md initial seed from ps1raf audit (loop task 83) 2026-04-18 19:07:13 +02:00
README.md initial seed from ps1raf audit (loop task 83) 2026-04-18 19:07:13 +02:00

llmwiki — ps1raf

An LLM-maintained markdown knowledge base for the ps1raf homelab server. Agents (primarily Claude Code) read and extend this wiki as they work; humans can read it too.

  • For agents: see LLMWIKI.md for the agent contract (how to read, when to extend, correction flow).
  • For humans: start at index.md to browse.
  • Recent activity: see CHANGELOG.md.

Design

Based on Karpathy's LLM Wiki pattern: a structured markdown directory that an agent builds and maintains as it works, so facts compound across sessions instead of decaying inside conversation context. Adapted for sysadmin/ops context rather than research.

Scope

What IS in scope:

  • Services deployed on ps1raf (Kanidm, Forgejo, Zabbix, …)
  • Host-level conventions (git flow, container style, secret storage, notifications)
  • Tool knowledge (step-ca CLI, myntfy, podman quirks)
  • External references (Forgejo URL, Kanidm URL, registered domains)
  • Corrections & lessons (what went wrong, how to avoid repeating)

What is NOT in scope:

  • User preferences (→ ~/.claude/projects/-home-raf/memory/)
  • Task state (→ loop.md, loop.log)
  • Harness config (→ CLAUDE.md, ~/.claude/settings.json)
  • Secrets (→ ~/.env)