New user flow:
1. Admin: python manage_passwords.py invite <username> → generates URL
2. User visits /setup/<token> → sets own password → logged in
3. User redirected to /setup/persona → fills name/emoji/description
4. persona_template.py generates all starter files → lands at /{user}/{persona}
Multiple personas:
- Header persona name is now a clickable dropdown listing all personas
- "New persona" link at bottom → /setup/persona (available to logged-in users)
- /api/personas endpoint returns persona list for current session user
New files:
- persona_template.py: generates IDENTITY/SOUL/PROTOCOLS/USER/HELP.md + data files
- routers/onboarding.py: /setup/{token}, /setup/persona GET+POST
- static/setup.html: two-step form (password → persona), emoji picker, mobile-friendly
Updated:
- auth_utils.py: create_invite(), validate_invite(), consume_invite()
- manage_passwords.py: invite command with URL output
- auth_middleware.py: /setup/* prefix is public (invite tokens need no auth)
- routers/ui.py: /api/personas endpoint; post-login redirect if no personas
- static/app.js: persona switcher dropdown with navigation + Add persona link
- static/style.css: .persona-switcher, .persona-dropdown, mobile adjustments
Mobile: login/setup pages are card-centered with responsive padding;
dropdown avoids edge-clipping on narrow screens; logout button stays visible.
All 80 tests pass.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Cortex / Inara — Project Root
Owner: Scott Idem (One Sky IT / Danger Zone) Started: 2026-03-04 Status: Active development
"You can't stop the signal."
Cortex is a self-hosted multi-agent AI platform. It supports multiple users, each with their own named AI persona. Inara (Scott's persona) and Tina (Holly's persona) are the initial instances.
Quick Orientation
| Directory | What it is |
|---|---|
cortex/ |
FastAPI service — dispatcher, routing, LLM backends, session management |
home/ |
User and persona data (home/{username}/persona/{name}/) |
home/scott/persona/inara/ |
Inara identity, memory, and context files |
home/holly/persona/tina/ |
Tina identity, memory, and context files |
docs/ |
Integration reference docs (NC Talk bot, etc.) |
documentation/ |
Architecture decisions, project plans, agent task lists |
Multi-User Layout
Persona data lives in a two-level tree modelled on Linux home directories:
home/
scott/
persona/
inara/ ← IDENTITY.md, SOUL.md, MEMORY_*.md, sessions/, TASKS.json, …
holly/
persona/
tina/
[username]/
persona/
[name]/
Each HTTP request includes user and persona fields. The service validates both against
the home/ tree before routing. ContextVars ensure per-request isolation in async code.
Naming rules (same as Linux usernames): lowercase letters, digits, _, -; must start
with a letter or underscore; max 32 characters. Example: scott, holly, my_ai-v2.
Running Cortex
Cortex runs as a systemd user service (no sudo required).
# Start / stop / restart
systemctl --user start cortex
systemctl --user stop cortex
systemctl --user restart cortex
# Status and logs
systemctl --user status cortex
journalctl --user -u cortex -f
# Web UI
http://localhost:8000 (or cortex.dgrzone.com on WireGuard)
The service starts automatically at boot via loginctl enable-linger.
Service file: ~/.config/systemd/user/cortex.service
Config lives in cortex/config.py and a .env file at the project root (not tracked — see .env.default).
Key Documentation
| File | Purpose |
|---|---|
documentation/TODO__Agents.md |
Active task list — read first |
documentation/ARCH__Intelligence_Layer.md |
Intelligence layer architecture (orchestrator, dev agents, knowledge) |
docs/NEXTCLOUD_TALK_BOT.md |
NC Talk bot setup |
home/scott/persona/inara/IDENTITY.md |
Inara persona and identity |
home/scott/persona/inara/HELP.md |
In-app help content (rendered in UI) |
home/scott/persona/inara/PROTOCOLS.md |
Inara behavioral protocols |
~/agents_sync/projects/CORTEX.md |
High-level project vision and phases |
Architecture at a Glance
[User / Cron / Webhook]
↓
Cortex Dispatcher (FastAPI, cortex/)
├─ POST /chat — direct to LLM (streaming SSE)
├─ POST /orchestrate — Gemini tool loop → Claude response
├─ POST /webhook/nextcloud — Nextcloud Talk bot
└─ POST /webhook/google — Google Chat Add-on
↓
LLM Backend(s)
• Claude CLI — primary reasoning, coding, long-context
• Gemini CLI — secondary / cost routing
• Gemini API — orchestrator tool loop (separate from Gemini CLI)
• Ollama — offline/private (scott_gaming, future)
↓
Persona context loaded from home/{user}/persona/{name}/
See documentation/ARCH__Intelligence_Layer.md for the orchestrator/responder and dev-agent architecture.
Inara / Tina
Each persona has its own identity, memory, and session history.
They are not tied to a specific LLM model — the name is fixed, the backend varies.
Context is loaded at request time from home/{user}/persona/{name}/ via cortex/context_loader.py.
| User | Persona | Description |
|---|---|---|
| scott | inara | Scott's primary AI assistant |
| holly | tina | Holly's primary AI assistant |
Channels
| Channel | Status | Notes |
|---|---|---|
| Web UI | Live | https://cortex.dgrzone.com (basic auth) |
| Nextcloud Talk | Live | HMAC-signed webhook, async reply |
| Google Chat | Live | Workspace Add-on, JWT auth |
Testing
cd cortex
.venv/bin/python -m pytest tests/ -q
80 tests covering API endpoints, persona routing, tool functions, and security.
Related Projects
| Project | Path |
|---|---|
| Aether Platform API | ~/OSIT_dev/aether_api_fastapi/ |
| Aether Frontend | ~/OSIT_dev/aether_app_sveltekit/ |
| Fleet coordination | ~/agents_sync/ |