Implements LLM-compiled wiki layer between raw session logs and live CONTEXT.md, inspired by Karpathy's knowledge base workflow. Adds wiki/ directory structure, article templates, spec docs, and seeds first two articles (Cascades of Tucson, GuruRMM) from 60+ session logs. Updates CLAUDE.md to check wiki first on all context-loading triggers. Captures verified ACG IP/hostname map and Neptune physical-location clarification (Dataforth D2, subnet overlap TODO) in memory. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
860 B
860 B
type, name, display_name, last_compiled, compiled_by, sources, backlinks
| type | name | display_name | last_compiled | compiled_by | sources | backlinks |
|---|---|---|---|---|---|---|
| system | <hostname> | <Hostname> | YYYY-MM-DD | <session_id> |
Identity
- Hostname: ...
- IP: ...
- Role: ...
- Location: Physical | VM on
- OS: ...
- Tailscale IP: ... (if applicable)
Specs
(CPU, RAM, disk, NIC — or VM config: vCPU, vRAM, virtual disk)
Services
| Service | Port | Notes |
|---|
Access
- SSH:
ssh user@IP(key in vault:infrastructure/<name>/...) - RDP: IP:port (if applicable)
- Console: iDRAC / Proxmox / Unraid UI / etc.
- Vault path:
infrastructure/<name>/
Known Issues & Quirks
(Historical problems, workarounds, things that have surprised us — the stuff not in any doc)
Backlinks
(Projects running on this system, clients whose infra lives here)