Add vault content - WORK folder, Tasks, Projects, Summaries, Templates

2026-02-24 09:46:07 -06:00
parent bc3284ad69
commit c402fb1161
41 changed files with 4299 additions and 0 deletions
--- a/Projects/Coding
+++ b/Projects/Coding
@@ -0,0 +1,86 @@
+# Coding Workflow
+
+## Environment
+- **Primary Channel:** Discord #coding (1468627455656067074)
+- **Repository:** whoisfrost/controls-web (Lassite controls internal website)
+- **Model:** kimi-k2.5:cloud (home-assistant), qwen3-coder-next:cloud (coding)
+
+---
+
+## Git Workflow
+
+### Branch Strategy
+| Branch | Purpose |
+|--------|---------|
+| `main` | Stable/production branch |
+| `dev` | Testing/playground branch |
+| `feature/*` | Specific changes (deleted after merge) |
+
+### Deployment Process
+```
+Work PC → GitHub (dev) → Dev Server (pulls dev) → Live Server (pulls main)
+```
+
+### Workflow Steps
+1. Create feature branch from dev
+2. Work and commit
+3. Push feature branch to GitHub
+4. Merge feature → dev
+5. Test on dev server
+6. Merge dev → main
+7. Deploy to live server
+
+### Commands
+```bash
+git checkout -b dev              # Create dev branch
+git push origin dev              # Push dev branch
+git checkout -b feature-name     # Create feature branch
+git push origin feature-name     # Push feature
+git checkout dev
+git merge feature-name           # Merge into dev
+git push origin dev
+git checkout main
+git merge dev                  # After testing
+git push origin main
+```
+
+---
+
+## LAMP Stack
+
+### Local Development
+- **Dashboard:** `C:\web\htdocs\dashboard` (active project)
+- **Web Root:** `C:\web\htdocs\`
+- **Old Dashboard:** `/var/www/html/dashboardv2/` (ignore - archived)
+
+### Production
+- Dev server pulls from `dev` branch
+- Live server pulls from `main` branch
+
+---
+
+## Tools & Environment
+- **Shell:** Bash
+- **SSH, curl, jq**
+- **Node.js:** For Next.js/React projects
+- **Python:** For Flask backends
+
+---
+
+## Model Assignments (Confirmed 2026-02-10)
+
+| Channel | Model | Reason |
+|---------|-------|--------|
+| #home-assistant | kimi-k2.5:cloud | General purpose |
+| #coding | qwen3-coder-next:cloud | Optimized for code |
+| #projects | kimi-k2.5:cloud | General purpose |
+
+---
+
+## Related Projects
+- [[Mission Control Dashboard (Python)]] — Flask dashboard :5050
+- [[Mission Control Dashboard (Next.js)]] — React dashboard :3000 (completed)
+
+---
+
+*Status: Active | Updated: 2026-02-22*
--- a/Projects/Discord
+++ b/Projects/Discord
@@ -0,0 +1,90 @@
+# Discord Voice Bot (GLaDOS)
+
+## Overview
+Voice-controlled Discord bot with conversational AI — always available in #coding voice channel
+
+---
+
+## Location
+`/home/admin/.openclaw/workspace/discord-voice-bot/`
+
+---
+
+## Architecture (Completed 2026-02-08)
+
+### Components
+| Component | Endpoint | Purpose |
+|-----------|----------|---------|
+| **TTS** | 192.168.0.17:5050 | GLaDOS voice synthesis |
+| **STT** | 192.168.0.17:10300 | Whisper via Wyoming protocol |
+| **LLM** | 192.168.0.17:11434 | Ollama (qwen3-coder-next:cloud) |
+| **Auto-join** | On startup | Joins #coding voice channel |
+
+### Voice Pipeline
+```
+Wake Word → STT (Whisper) → LLM (Ollama) → TTS (GLaDOS) → Voice Output
+```
+
+---
+
+## Commands
+- `!join` — Join voice channel
+- `!leave` — Leave voice channel
+- `!test [text]` — Test TTS synthesis
+- `!listen` — 5-second voice recording (7-10 sec latency)
+
+---
+
+## MCP Integration (OpenClaw Bridge)
+
+### MCP Tools Available via Voice
+- `list_projects()` — "What am I working on?"
+- `create_project(name)` — Start new project
+- `add_task(project, task)` — Add tasks via voice
+- `update_task_status(taskId, status)` — Mark complete
+- `get_project_status()` — Check overall progress
+
+### MCP Server Config
+```yaml
+mcp_servers:
+  - name: "openclaw"
+    transport: "stdio"
+    command: "python"
+    args:
+      - "C:\Users\admin\.openclaw\workspace\discord-voice-bot\openclaw_mcp_server.py"
+```
+
+---
+
+## Files Created
+- `openclaw_mcp_server.py` — FastMCP server exposing OpenClaw tools
+- `main.py` — Bot implementation using discord.py, wyoming
+- `config.yaml` — Configuration
+- `requirements.txt` — Dependencies (discord.py, requests, numpy, wyoming)
+
+---
+
+## What Changed (v2)
+- Removed GLaDOS direct dependencies (simpler integration)
+- Uses existing services (Whisper, Ollama, HTTP TTS)
+- Auto-joins voice channel on startup
+- Clean async architecture
+- MCP bridge for OpenClaw integration
+
+---
+
+## Known Limitations
+- Voice latency: 7-10 seconds for `!listen` (5s recording + processing)
+- Not conversational due to latency
+- Best for command-based interactions, not real-time chat
+
+---
+
+## Status
+✅ **COMPLETED** — Operational in #coding voice channel
+
+Bot auto-joins on startup and accepts voice commands via MCP bridge.
+
+---
+
+*Status: Complete | Version: 2.0 | Updated: 2026-02-22*
--- a/Projects/Home
+++ b/Projects/Home
@@ -0,0 +1,100 @@
+# Home Assistant
+
+## Environment
+- **URL:** http://192.168.0.39:8123
+- **Auth Token:** eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiIxMTRhMDMwYjNhNjg0N2JiYWY2YmUxNmY4YTBhYjVkZiIsImlhdCI6MTc3MDE3NTU0NSwiZXhwIjoyMDg1NTM1NTQ1fQ.8xxRzURj0NoFoo_UdtH34IXcuBX6fSpofdA8GjCK-B4
+- **MQTT Broker:** 192.168.0.39:1883 (corey/41945549)
+- **Status:** 🔄 In Progress (entity cleanup ongoing)
+- **Discord Channel:** #home-assistant (1466074219829006599)
+
+---
+
+## Room-Assistant (Bluetooth Presence) - WORKING! ✅
+
+**What it does:**
+- Pi Zero W BLE scans for known phones
+- Reports to HA via MQTT
+- Creates device_tracker entities per room
+- Multi-Pi setup gives room-level presence
+
+### Hardware
+- **Pi 1:** livingroom-pi (192.168.0.95)
+- **Bluetooth MAC:** B8:27:EB:50:C9:40
+- **SSH:** admin / 41945549
+- **SSH Key:** ~/.ssh/id_ed25519 (Windows SSH quirk - needs manual workarounds)
+
+### Phone Tracking
+- **Corey's Phone:** B0:C2:C7:07:28:B4 (motorola razr 2024)
+- **Phone MAC Discovery:**
+  - iPhone: Settings → About → Bluetooth
+  - Android: Settings → About Phone → Status → Bluetooth address
+
+### Room-Assistant Config (`/home/admin/config/local.yml`)
+```yaml
+mqtt:
+  host: "192.168.0.39"
+  port: 1883
+  username: "corey"
+  password: "41945549"
+bluetooth:
+  adminToken: "AF07072FBAC1FD6281FBE765DF6D841E"
+  timeout: 60
+  addresses:
+    - "b0:c2:c7:07:28:b5"  # Corey's phone MAC
+settings:
+  room: "LivingRoom"
+```
+
+### Home Assistant Entities Created
+- `sensor.livingroom_cluster_size`
+- `sensor.livingroom_cluster_leader`
+- `device_tracker.livingroom_phone` (when phone in range)
+
+### Key Config Notes
+- Config location: `/home/admin/config/local.yml` (NOT in room-assistant subdir)
+- Config format: keys at root level (v2.x), no "global." prefix
+- mdns module needed: `sudo npm install -g mdns` (for cluster discovery)
+- RSSI threshold: `-70` (adjustable for range)
+
+---
+
+## Current Tasks
+
+### High Priority
+- [ ] Entity cleanup (972 devices in spreadsheet)
+- [x] Fix hallway sensor battery (1%)
+- [ ] Add Kathy's phone to room-assistant config
+
+### In Progress
+- [x] Room-assistant setup and working
+- [x] Phone MAC paired and tracking
+- [ ] Multi-Pi expansion (clone SD after first Pi stable)
+
+---
+
+## Setup Workflow (for future Pis)
+1. Flash Pi OS Lite to SD card
+2. Enable SSH + WiFi via Pi Imager
+3. Copy config files to Pi
+4. Run `sudo ./setup-room-assistant.sh`
+5. Script prompts for: room name, MQTT creds, phone MACs
+
+---
+
+## Files Created
+- `room-assistant-config.yml` — BLE presence config template
+- `setup-room-assistant.sh` — Automated Pi setup script
+- `ROOM_ASSISTANT_SETUP.md` — Complete setup documentation
+- `temp/write_ha_names.py` — Push entity changes back to HA
+
+---
+
+## Integration Points
+- HA REST API (native)
+- MQTT (for room-assistant)
+- Mission Control dashboard (for display)
+- Discord notifications (alerts)
+
+---
+
+*Status: Room presence working, entity cleanup ongoing | Updated: 2026-02-22*
--- a/Projects/Memory
+++ b/Projects/Memory
@@ -0,0 +1,144 @@
+# Memory System
+
+## Architecture Evolution
+Started as flat file system, evolved to hierarchical hybrid (file + SQL) architecture.
+
+---
+
+## Current Stack (February 2026)
+
+### 1. Hierarchical File Structure
+Based on ucsandman's design — index + drill-down:
+
+`
+memory/
+├── MEMORY.md                 # ~2.4k token index (was 5-10k)
+├── people/
+│   └── corey.md              # User details
+├── projects/
+│   ├── mission-control-python.md
+│   ├── home-assistant.md
+│   ├── memory-system.md
+│   └── [others]
+├── decisions/
+│   └── 2026-02.md            # Monthly decisions
+└── 2026-02-21.md             # Daily notes
+`
+
+**Benefits:**
+- Session start: ~2.4k tokens (was 5-10k)
+- On-demand drill-down: ~1k tokens per file
+- **~70% token savings**
+
+### 2. SQLite Database
+- **Location:** ~/.openclaw/memory.db
+- **Tables:**
+  - memory_cells — Structured data
+  - scenes — Context/grouping
+  - memory_fts — Full-text search
+- **Extraction:** Memory Worker agent (3 AM daily)
+
+### 3. Supermemory.ai Backup
+- **Schedule:** Daily 2 AM
+- **Script:** scripts/backup-memory.py
+- **History:** Document IDs tracked per backup
+
+### 4. MySQL Mirror (Legacy)
+- **Host:** localhost:3306
+- **Database:** clawdbot_projects
+- **Tables:** daily_notes, long_term_memories, action_items, backup_logs, sessions
+- **User:** AlexAI/alexisabignerd
+- **Status:** Functional but not actively used
+
+---
+
+## Key Decisions
+
+| Date | Decision | Status |
+|------|----------|--------|
+| 2026-02-09 | Supermemory backup with cron | Active |
+| 2026-02-12 | workspace-context.md for temp state | Active |
+| 2026-02-16 | Hybrid File + SQLite (not MySQL) | Active |
+| 2026-02-18 | Hierarchical index + drill-down | Live |
+| 2026-02-20 | Memory Worker writes to SQLite | Working |
+
+---
+
+## Ollama Memory Embeddings (2026-02-10)
+
+**Setup:**
+- Installed skill from https://clawhub.ai/vidarbrekke/ollama-memory-embeddings
+- Uses Ollama /v1/embeddings endpoint
+- Replaces node-llama-cpp for local embeddings
+
+**Trade-off:**
+- ✅ Faster, OpenAI-compatible API
+- ⚠️ Two embedding universes: old (node-llama-cpp) vs new (Ollama)
+- Historical memories may search differently
+
+---
+
+## Workers
+
+### Memory Worker Daily
+- **Schedule:** 3 AM
+- **Task:** Extract structured data → SQLite
+- **Extraction source:** memory/YYYY-MM-DD.md files
+- **Output:** memory.db + Discord report
+
+### Job Verifier Daily  
+- **Schedule:** 9 AM
+- **Task:** Check overnight job statuses
+- **Reports to:** #alerts channel
+
+---
+
+## Integration Points
+
+| System | Direction | Method |
+|--------|-----------|--------|
+| OpenClaw Memory Search | Read | semantic search |
+| SQLite Database | Read/Write | memory tool |
+| Supermemory | Write (backup) | API |
+| Obsidian Vault | Write (export) | notesmd-cli |
+| MySQL | Legacy | Direct SQL |
+
+---
+
+## Skills Related
+
+| Skill | Purpose |
+|-------|---------|
+| ollama-memory-embeddings | Ollama-based embeddings |
+| memory-to-obsidian | Export notes to Obsidian |
+| ez-cronjob | Fix cron scheduling issues |
+| self-improving-agent | Log errors/corrections |
+
+---
+
+## Troubleshooting Notes
+
+**Cron deadlock bug:**
+- Issue: cron tool hangs
+- Fix: Use openclaw cron CLI via exec instead
+
+**Context bloat:**
+- Issue: 256k limit hit frequently
+- Fix: Spawn sub-agents for complex tasks
+
+**Session recovery:**
+- workspace-context.md survives crashes
+- Cleaned daily at ~11 PM
+
+---
+
+## Future Ideas
+
+1. SQL → HA Dashboard integration
+2. Automated presence tracking export
+3. Memory stats/analytics in Mission Control
+4. Re-embed historical memories for consistency
+
+---
+
+Status: Live | Last Major Update: 2026-02-18 (Hierarchical restructure)
--- a/Architecture.md
+++ b/Architecture.md
@@ -0,0 +1,261 @@
+---
+title: Memory System Architecture
+category: Projects
+project: Memory System
+type: Architecture/Documentation
+status: complete
+date: 2026-02-16
+last_updated: 2026-02-23
+tags: [memory, architecture, openclaw, system-design, data-flow]
+source_file: memory_system_architecture.md
+---
+
+# Memory System Architecture
+
+*Diagram of how information flows and persists in the OpenClaw system*
+
+---
+
+## Overview
+
+```
+┌─────────────────────────────────────────────────────────────────────────────┐
+│                         INFORMATION FLOW                                     │
+└─────────────────────────────────────────────────────────────────────────────┘
+
+    User Conversation
+           │
+           ▼
+┌─────────────────────┐     ┌─────────────────────┐     ┌─────────────────────┐
+│   ME (Main Agent)   │────▶│   Memory Worker     │────▶│   SQLite Database   │
+│   (Real-time)       │     │   (Daily 3 AM)      │     │   (Structured)      │
+└─────────────────────┘     └─────────────────────┘     └─────────────────────┘
+           │                           │                           │
+           │                           │                           │
+           ▼                           ▼                           ▼
+┌─────────────────────┐     ┌─────────────────────┐     ┌─────────────────────┐
+│   Daily Notes       │     │   Query Interface   │     │   Stats/Search      │
+│   (memory/*.md)     │◄────│   (On Demand)      │◄────│   (SQL/FTS)        │
+└─────────────────────┘     └─────────────────────┘     └─────────────────────┘
+           │
+           ▼
+┌─────────────────────┐
+│   MEMORY.md         │
+│   (Curated)         │
+└─────────────────────┘
+           │
+           ▼
+┌─────────────────────┐
+│   Supermemory.ai    │
+│   (Cloud Backup)    │
+└─────────────────────┘
+```
+
+---
+
+## Storage Layers (By Speed & Persistence)
+
+### 1. ⚡ Session RAM (Transient)
+| Aspect | Details |
+|--------|---------|
+| **What** | Current conversation context, tool outputs, working memory |
+| **Writes** | Every message I process |
+| **When** | Real-time during conversation |
+| **Stored** | Until session ends or compaction (30 min - 4 hours) |
+| **Survives** | ❌ Session crash ❌ Gateway restart |
+| **Size** | ~100K-250K tokens |
+
+**Risk:** Compaction clears this. The "danger zone" is between last tool use and compaction.
+
+---
+
+### 2. 📝 Daily Notes (Short-term)
+| Aspect | Details |
+|--------|---------|
+| **What** | Raw daily activity, decisions, tasks, errors |
+| **Writes** | Pre-compaction flush (automatic) + manual captures |
+| **When** | End of productive sessions, before `/compact` |
+| **Stored** | `memory/YYYY-MM-DD.md` |
+| **Survives** | ✅ Session crash ✅ Gateway restart |
+| **Retention** | ~30-90 days (manually reviewed) |
+| **Format** | Free-form markdown |
+
+**Written by:** Me (main agent) during heartbeat or EOD ritual
+
+---
+
+### 3. 🧠 MEMORY.md (Long-term)
+| Aspect | Details |
+|--------|---------|
+| **What** | Curated important info, distilled from daily notes |
+| **Writes** | Manual review of daily notes, during heartbeats |
+| **When** | Every few days, or when something critical happens |
+| **Stored** | `MEMORY.md` in workspace root |
+| **Survives** | ✅ Everything (file-based) |
+| **Retention** | Permanent (manual curation) |
+| **Format** | Human-readable markdown |
+
+**Written by:** Me, after reviewing daily notes
+
+---
+
+### 4. 📊 SQLite Database (Structured)
+| Aspect | Details |
+|--------|---------|
+| **What** | Structured: tasks, decisions, facts, projects with salience |
+| **Writes** | Memory Worker (automated daily extraction) |
+| **When** | Daily 3:00 AM (cron job) |
+| **Stored** | `~/.openclaw/memory.db` |
+| **Survives** | ✅ File-based |
+| **Retention** | Permanent (until manual deletion) |
+| **Format** | Relational: cells, scenes, FTS index |
+
+**Written by:** Memory Worker agent (spawned via cron)
+
+**Schema:**
+```sql
+memory_cells: id, scene, cell_type, salience, content, source_file, created_at
+scenes: scene, summary, item_count, updated_at
+memory_fts: full-text search index
+```
+
+---
+
+### 5. 🌐 Supermemory.ai (Cloud)
+| Aspect | Details |
+|--------|---------|
+| **What** | Full backup of all memory files |
+| **Writes** | Supermemory Backup job (automated) |
+| **When** | Daily 2:00 AM |
+| **Stored** | Supermemory.ai cloud service |
+| **Survives** | ✅ Disk failure ✅ Workspace loss |
+| **Retention** | Cloud provider dependent |
+| **Format** | API-uploaded documents |
+
+**Written by:** Python script via cron job
+
+---
+
+### 6. 📋 Workspace Context (Session Bridge)
+| Aspect | Details |
+|--------|---------|
+| **What** | Current conversation, in-progress, finished today |
+| **Writes** | Real-time during session |
+| **When** | Continuously updated |
+| **Stored** | `workspace-context.md` |
+| **Survives** | ✅ Session crash ✅ Channel switch |
+| **Retention** | Cleared nightly (~11 PM) |
+| **Format** | Structured markdown |
+
+**Special:** Survives between channels and session crashes. Cleared daily.
+
+---
+
+## Retention Summary
+
+| Layer | Retention | Cleared When | Backup |
+|-------|-----------|--------------|--------|
+| Session RAM | Minutes-hours | Compaction | ❌ |
+| Workspace Context | ~24 hours | 11 PM nightly | ❌ |
+| Daily Notes | 30-90 days | Manual archive | Supermemory |
+| MEMORY.md | Permanent | Manual edit | Supermemory |
+| SQLite DB | Permanent | Manual delete | ❌ (local only) |
+| Supermemory | Permanent | Cloud provider | N/A (is backup) |
+
+---
+
+## Write Triggers
+
+```
+Every Message
+      │
+      ├─► Session RAM (immediate)
+      │
+      └─► If important ┐
+                       ▼
+              workspace-context.md
+                       │
+          Pre-compaction ┤
+                       ▼
+              memory/YYYY-MM-DD.md
+                       │
+         Periodic review ┤
+                       ▼
+                   MEMORY.md
+                       │
+              Daily 2 AM ┤
+                       ▼
+                 Supermemory.ai
+                       │
+              Daily 3 AM ┤
+                       ▼
+                 SQLite Database
+```
+
+---
+
+## Access Patterns
+
+### I (Main Agent) Access:
+| Source | When | Purpose |
+|--------|------|---------|
+| MEMORY.md | Every session startup | Core identity, user prefs, important facts |
+| USER.md | Every session startup | Who Corey is |
+| SOUL.md | Every session startup | How I should behave |
+| workspace-context.md | Every session startup | Current conversation state |
+| memory/*.md | During heartbeats | Recent context |
+| SQLite DB | On demand | Structured queries ("what tasks pending?") |
+
+### Memory Worker Access:
+| Source | When | Purpose |
+|--------|------|---------|
+| IDENTITY.md | Daily 3 AM | Who it is |
+| SOUL.md | Daily 3 AM | Its mission |
+| HEARTBEAT.md | Daily 3 AM | What to do (the script) |
+| memory/YYYY-MM-DD.md | Daily 3 AM | What to extract |
+| SQLite DB | Daily 3 AM | Where to write |
+
+---
+
+## Failure Recovery
+
+### Scenario: Session Crash
+- ✅ **Survives:** Files (MEMORY.md, daily notes, workspace-context)
+- ❌ **Lost:** Session RAM (compaction would have cleared anyway)
+- 🔄 **Recovery:** Read files on restart, reconstruct context
+
+### Scenario: Gateway Restart
+- ✅ **Survives:** All files, SQLite DB
+- ❌ **Lost:** Session state, cron job state (must recreate jobs)
+- 🔄 **Recovery:** Gateway restart, verify cron jobs running
+
+### Scenario: Disk Failure
+- ✅ **Survives:** Supermemory.ai (cloud backup)
+- ❌ **Lost:** Local files, SQLite DB
+- 🔄 **Recovery:** Restore from Supermemory, recreate DB (re-extract from notes)
+
+---
+
+## Key Insights
+
+1. **Text > Brain** — Files persist, my session doesn't
+2. **Daily notes = raw, MEMORY.md = curated** — Filter noise from signal
+3. **Worker = automated structuring** — Don't have to manually organize everything
+4. **Hybrid = best of both** — Human-readable + machine-queryable
+5. **Multiple backups** — Local files + cloud (Supermemory) + structured DB
+
+---
+
+## Related Files
+
+- [[Memory System]] — OpenClaw summary (in OpenClaw/ folder)
+- MEMORY.md — Curated long-term memory
+- memory/YYYY-MM-DD.md — Daily notes
+- workspace-context.md — Session bridge
+- ~/.openclaw/memory.db — Structured SQLite database
+
+---
+
+*Generated: 2026-02-16*  
+*Copied to Obsidian: 2026-02-23*  
+*System Version: Multi-agent with SQLite extraction*
--- a/Projects/Mission
+++ b/Projects/Mission
@@ -0,0 +1,40 @@
+# Mission Control Dashboard (Python)
+
+**Location:** C:\web\htdocs\mission-control-py
+**URL:** http://localhost:5050
+**Tech:** Python/Flask + MySQL + Home Assistant API
+
+## Quick Reference
+
+| Command | Action |
+|---------|--------|
+| Run | cd C:\web\htdocs\mission-control-py && python app.py |
+| Port | 5050 (Frigate-safe) |
+| Restart | Auto-reloads on file changes |
+
+## Pages
+
+| Route | Purpose |
+|-------|---------|
+| / | Gateway status, Cron jobs, Weather |
+| /admin | Projects/Tasks CRUD |
+| /news | News briefs archive |
+| /alerts | System alerts |
+| /calendar | HA calendar + F1 races |
+| /memory | Memory file stats |
+
+## Features
+
+- **Caching:** 5-minute TTL for Gateway/Cron/Weather
+- **Weather:** From HA weather.home entity
+- **News:** Cron-fed JSON at 8 AM daily
+- **Calendar:** HA integration (date range bug known)
+
+## Known Issues
+
+| Issue | Status |
+|-------|--------|
+| Calendar >10 days not showing | Known |
+| Calendar agent creates cron not events | Known |
+
+_Last updated: 2026-02-20_
--- a/Projects/Multi-User
+++ b/Projects/Multi-User
@@ -0,0 +1,203 @@
+---
+title: Multi-User Agent Architecture
+category: Projects
+project: System Architecture
+type: Research/Design
+status: planning
+date: 2026-02-24
+tags: [openclaw, multi-user, architecture, collaboration, discord, design]
+---
+
+# Multi-User Agent Architecture
+
+**Question:** What's the best way to handle multiple users using one agent for tasks and project management?
+
+**Date:** 2026-02-24  
+**Status:** Planning/Research
+
+---
+
+## Executive Summary
+
+Four approaches ranging from simple (separate channels) to complex (multi-agent). Recommendation: **Start with Option 1 (Separate Channels)** and add frontmatter tagging (Option 3) as needed.
+
+---
+
+## Option 1: Separate Channels Per User ⭐ RECOMMENDED
+
+**Best for:** Small teams (2-5 people), clear separation
+
+### Setup
+```
+Discord Server:
+├── #home-assistant (shared - only you/active)
+├── #corey-projects (your own)
+├── #alice-projects (Alice's channel)
+├── #bob-projects (Bob's channel)
+└── #shared-projects (collaborative)
+```
+
+### How It Works
+- Each user gets their own channel
+- Agent has separate sessions for each
+- Context isolation = no cross-contamination
+- Shared projects in #shared-projects
+
+### Pros
+- ✅ Total privacy per user
+- ✅ Simple to manage
+- ✅ One agent, multiple sessions
+- ✅ User-specific memory stays isolated
+
+### Cons
+- More channels to manage
+- Shared projects need explicit cross-posting
+
+---
+
+## Option 2: User Tagging System (Hybrid)
+
+**Best for:** Shared workspace with user-aware tasks
+
+### Setup
+- One shared channel (#projects)
+- Users tag messages: `@alice` or `#for-alice`
+- Or: "Task for Alice: ..."
+
+### How It Works
+- Agent identifies user from message content
+- Store tasks with user attribution
+- Query by user when needed
+
+### Example Workflow
+```
+Corey: #task for @alice - Review the architecture doc
+Alice: (in same channel) I reviewed it, looks good
+Corey: #task for @bob - Deploy the update
+```
+
+### Pros
+- ✅ Single channel
+- ✅ Collaborative feel
+- ✅ Clear ownership
+
+### Cons
+- Requires discipline with tagging
+- Context can get messy
+- Privacy is opt-in (explicit tags)
+
+---
+
+## Option 3: User Profiles in Frontmatter
+
+**Best for:** Shared Obsidian vault, Dataview queries
+
+### Setup
+- Tasks/projects have frontmatter with `assignee: alice`
+- Query using Dataview: `WHERE assignee = "alice"`
+
+### Example Task
+```markdown
+---
+title: Review architecture
+project: Memory System
+assignee: alice
+status: todo
+due: 2026-02-25
+---
+
+Alice needs to review the memory system architecture.
+```
+
+### Query
+```dataview
+TABLE status, due
+FROM "Tasks"
+WHERE assignee = "alice" AND status = "todo"
+SORT due ASC
+```
+
+### Pros
+- ✅ Perfect for Obsidian
+- ✅ Dataview-powered dashboards
+- ✅ Automatic organization
+
+### Cons
+- Requires frontmatter discipline
+- Real-time chat = harder to manage
+
+---
+
+## Option 4: Multi-Agent (Advanced)
+
+**Best for:** Teams where each person wants their own agent
+
+### Setup
+- Each user has their own OpenClaw instance
+- Shared resources via Obsidian/SQLite
+- Sync via git or shared database
+
+### How It Syncs
+- Obsidian vault is shared (Syncthing/Nextcloud)
+- Both agents read/write same files
+- Different identities, same data
+
+### Pros
+- ✅ Full separation
+- ✅ Personalized agents
+- ✅ Shared long-term memory
+
+### Cons
+- Complex setup
+- More resources (multiple agents)
+- Merge conflicts possible
+
+---
+
+## Recommendation
+
+**Start with:** Option 1 (Separate Channels)
+
+**Why:**
+- Simplest to implement
+- No context pollution
+- Easy permissions (Discord native)
+- Can add Option 3 (Frontmatter) later
+
+**Hybrid Approach:**
+- Private channels per user (`#alice-projects`, `#bob-projects`)
+- Shared channel for collaboration (`#team-projects`)
+- Obsidian vault is shared with user-tagged frontmatter
+
+---
+
+## Decision Matrix
+
+| Factor | Option 1 | Option 2 | Option 3 | Option 4 |
+|--------|----------|----------|----------|----------|
+| **Privacy** | High | Medium | High | High |
+| **Setup Complexity** | Low | Low | Medium | High |
+| **Collaboration** | Medium | High | Medium | Medium |
+| **Scalability** | Medium | High | High | High |
+| **Discord Channels** | Many | One | N/A | Many |
+
+---
+
+## Next Steps
+
+1. **Define users:** How many people? Technical level?
+2. **Privacy check:** Do users need isolation from each other?
+3. **Collaboration needs:** Shared projects vs individual work?
+4. **Pilot:** Start with Option 1, iterate based on feedback
+
+---
+
+## Related
+
+- [[Memory System]] — How agent memory works
+- [[Dataview Query Examples]] — Query by user/assignee
+
+---
+
+*Created: 2026-02-24*  
+*Based on discussion in #home-assistant*
--- a/Projects/Projects-Index.md
+++ b/Projects/Projects-Index.md
@@ -0,0 +1,70 @@
+---
+title: Projects Index
+category: Projects
+status: active
+last_updated: 2026-02-24
+tags: [projects, index, active, completed]
+---
+
+# Projects Index
+
+## Active Projects
+
+### Mission Control Python
+- Status: Live on :5050
+- Type: Dashboard
+- Tech: Flask + MySQL + HA API
+- Notes: 6 pages, cron integration, weather, calendar
+- Issues: Calendar date range bug, calendar agent bug
+
+### Home Assistant
+- Status: Entity cleanup ongoing
+- Type: Home Automation
+- Notes: 972 devices cleanup, Room-Assistant working
+
+### Memory System
+- Status: Hierarchical restructure complete
+- Type: Infrastructure
+- Notes: File + SQLite hybrid, Supermemory backups
+
+### Coding Workflow
+- Status: Active
+- Type: DevOps
+- Notes: Git/controls-web, Kimi/mini model split
+
+### Auto-Summarize Workflow {#sync}
+- Status: Active
+- Type: Agent Capability
+- Notes: "/summarize [URL]" → fetch → summarize → save to Summaries/
+- Works with: Any web URL
+
+### Multi-User Agent Architecture
+- Status: Planning
+- Type: System Design
+- Notes: Researching multi-user approaches for task/project management
+- Options: Separate channels, tagging system, frontmatter, multi-agent
+- Decision: Start with Option 1 (separate Discord channels)
+
+## Completed Projects
+
+### Discord Voice Bot (GLaDOS)
+- Status: Completed 2026-02-08
+- Type: Voice Bot
+- Notes: Always in #coding voice
+
+### Proton Mail Bridge
+- Status: Completed 2026-02-18
+- Type: Email Integration
+- Notes: IMAP/SMTP tested
+
+## How to Sync
+1. Edit any project note in Obsidian
+2. Tell me to sync
+3. I read the updated note and update my memory
+
+### How to Summarize
+1. Type: `/summarize [URL]`
+2. I fetch, summarize, and save to `Summaries/`
+3. Confirm and link back to you
+
+Last Updated: 2026-02-23
--- a/Projects/Proton
+++ b/Projects/Proton
@@ -0,0 +1,84 @@
+# Proton Mail Bridge
+
+## Overview
+Email integration via Proton Mail Bridge for IMAP/SMTP access. Gives local IMAP/SMTP endpoints that can be used with standard email clients.
+
+---
+
+## Connection Details
+- **IMAP Server:** 127.0.0.1:1143
+- **SMTP Server:** 127.0.0.1:1025
+- **Username:** alexthenerdyai@proton.me
+- **Security:** AUTH=PLAIN (local connection only)
+- **Bridge Version:** Proton Mail Bridge 03.22.00 - gluon
+
+---
+
+## Test Results (2026-02-18)
+✅ Connected successfully to Bridge IMAP
+✅ Authenticated with Bridge password
+✅ Retrieved folder list (10 folders found)
+✅ INBOX has 3 messages, all unread
+
+---
+
+## Folders
+- INBOX
+- Sent
+- Drafts
+- Starred
+- Archive
+- Spam
+- Trash
+- All Mail
+- Folders
+- Labels
+
+---
+
+## Capabilities
+- Read emails from INBOX
+- Search, mark read/unread, move messages
+- Send emails via SMTP
+- Full folder management
+
+---
+
+## Files Created
+- `tools/proton_imap_test.py` — Initial test script
+- `tools/proton_imap_simple.py` — Working IMAP test script
+
+---
+
+## Potential Uses
+- Daily email digest
+- Notifications
+- Automated responses
+- Email-based triggers (IFTTT style)
+
+---
+
+## Next Steps
+- [ ] Integrate with cron jobs for email-based actions
+- [ ] Create email notification system
+- [ ] Set up email-to-Discord forwarding
+- [ ] Build email digest bot
+
+---
+
+## Technical Notes
+- Bridge runs locally (127.0.0.1)
+- AUTH=PLAIN is safe because connection is local only
+- Standard Python imaplib/smtplib libraries work
+- No Proton-specific libraries needed
+
+---
+
+## Status
+✅ **FUNCTIONAL** — Bridge connected and tested
+
+Ready for automation integration.
+
+---
+
+*Status: Complete & Tested | Updated: 2026-02-22*