- CLAUDE.md: add new auth/onboarding files to directory map, update security section (JWT/bcrypt/invite details), expand recently completed - README.md: fix Web UI auth description, add User Management section - TODO__Agents.md: mark NC Talk docs and auth/onboarding complete, update Holly onboarding plan to reflect single-instance multi-user approach - docs/NEXTCLOUD_TALK_BOT.md: complete guide — occ commands, nginx config, clarify incoming vs outgoing HMAC difference, multi-user note, full troubleshooting table - home/holly/persona/tina/: flesh out all four persona files with real content (DCC name origin, metal music, reading, foster cats, Holly's profile) - .gitignore: exclude home/**/auth.json, invite.json, profile.json Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Inara — Identity & Memory Layer
This directory is Inara's home. It contains everything needed to instantiate her as a consistent, persistent agent across any model or runtime.
Files
| File | Tier | Purpose |
|---|---|---|
SOUL.md |
Always | Core identity, traits, how she behaves |
IDENTITY.md |
Always | Name, vibe, emoji — the short card |
USER.md |
T1+ | Scott's profile — who she's helping |
MEMORY.md |
T2+ | Curated long-term memory (keep under 4k tokens) |
PROTOCOLS.md |
T2+ | Fleet rules, safety, delegation, memory management |
CONTEXT_TIERS.md |
Dispatcher | Which files to load per model context size |
sessions/ |
T3+ | Daily session logs (raw), format: YYYY-MM-DD.md |
Loading Order
Always load in this order to establish context before adding detail:
SOUL.mdIDENTITY.mdUSER.mdMEMORY.mdPROTOCOLS.md- Session files (most recent first)
See CONTEXT_TIERS.md for the full dispatcher spec.
Secrets
Credentials, API keys, and tokens live in .env only — never in these files.