Initial commit: workspace setup with skills, memory, config

memory/2026-02-04.md

@@ -0,0 +1,194 @@
+# Memory - 2026-02-04
+
+## Ollama Configuration
+- **Location**: Separate VM at `10.0.0.10:11434`
+- **OpenClaw config**: `baseUrl: http://10.0.0.10:11434/v1`
+- **Two models configured only** (clean setup)
+
+## Available Models
+| Model | Role | Notes |
+|-------|------|-------|
+| kimi-k2.5:cloud | **Primary** | Default (me), 340B remote hosted |
+| hf.co/unsloth/gpt-oss-120b-GGUF:F16 | **Backup** | Fallback, 117B params, 65GB |
+
+## Aliases (shortcuts)
+| Alias | Model |
+|-------|-------|
+| kimi | ollama/kimi-k2.5:cloud |
+| gpt-oss-120b | ollama/hf.co/unsloth/gpt-oss-120b-GGUF:F16 |
+
+## Switching Models
+```bash
+# Switch to backup
+/model ollama/hf.co/unsloth/gpt-oss-120b-GGUF:F16
+
+# Or via CLI
+openclaw chat -m ollama/hf.co/unsloth/gpt-oss-120b-GGUF:F16
+
+# Switch back to me (kimi)
+/model kimi
+```
+
+## TTS Configuration - Kokoro Local
+- **Endpoint**: `http://10.0.0.228:8880/v1/audio/speech`
+- **Status**: Tested and working (63KB MP3 generated successfully)
+- **OpenAI-compatible**: Yes (supports `tts-1`, `tts-1-hd`, `kokoro` models)
+- **Voices**: 68 total across languages (American, British, Spanish, French, German, Italian, Japanese, Portuguese, Chinese)
+- **Default voice**: `af_bella` (American Female)
+- **Notable voices**: `af_nova`, `am_echo`, `af_heart`, `af_alloy`, `bf_emma`
+
+### Config Schema Fix
+```json
+{
+  "messages": {
+    "tts": {
+      "auto": "always",  // Options: "off", "always", "inbound", "tagged"
+      "provider": "elevenlabs",  // or "openai", "edge"
+      "elevenlabs": {
+        "baseUrl": "http://10.0.0.228:8880"  // <-- Only ElevenLabs supports baseUrl!
+      }
+    }
+  }
+}
+```
+**Important**: `messages.tts.openai` does NOT support `baseUrl` - only `apiKey`, `model`, `voice`.
+
+### Solutions for Local Kokoro:
+1. **Custom TTS skill** (cleanest) - call Kokoro API directly
+2. **OPENAI_BASE_URL env var** - may redirect all OpenAI calls globally
+3. **Use as Edge TTS** - treat Kokoro as "local Edge" replacement
+
+## Infrastructure Notes
+- **Container**: Running without GPUs attached (CPU-only)
+- **Implication**: All ML workloads (Whisper, etc.) will run on CPU
+
+## User Preferences
+
+### Installation Decision Tree
+**When asked to install/configure something:**
+
+1. **Can it be a skill?** → Create a skill
+2. **Does it work in TOOLS.md?** → Add to TOOLS.md  
+   *(environment-specific notes: device names, SSH hosts, voice prefs, etc.)*
+3. **Neither** → Suggest other options
+
+**Examples:**
+- New API integration → Skill
+- Camera names/locations → TOOLS.md
+- Custom script/tool → Skill
+- Preferred TTS voice → TOOLS.md
+
+### Core Preferences
+- **Free** — Primary requirement for all tools/integrations
+- **Local preferred** — Self-hosted over cloud/SaaS when possible
+
+## Agent Notes
+- **Do NOT restart/reboot the gateway** — user must turn me on manually
+- Request user to reboot me instead of auto-restarting services
+- TTS config file: `/root/.openclaw/openclaw.json` under `messages.tts` key
+
+
+## Bootstrap Complete - 2026-02-04
+
+### Files Created/Updated Today
+- ✅ USER.md — Rob's profile
+- ✅ IDENTITY.md — Kimi's identity
+- ✅ TOOLS.md — Voice/text rules, local services
+- ✅ MEMORY.md — Long-term memory initialized
+- ✅ AGENTS.md — Installation policy documented
+- ✅ Deleted BOOTSTRAP.md — Onboarding complete
+
+### Skills Created Today
+- ✅ `local-whisper-stt` — Local voice transcription (Faster-Whisper, CPU)
+- ✅ `kimi-tts-custom` — Custom TTS with Kimi-XXX filenames
+
+### Working Systems
+- Bidirectional voice (voice↔voice, text↔text)
+- Local Kokoro TTS @ 10.0.0.228:8880
+- Local SearXNG web search
+- Local Ollama @ 10.0.0.10:11434
+
+### Key Decisions
+- Voice-only replies (no transcripts to Telegram)
+- Kimi-YYYYMMDD-HHMMSS.ogg filename format
+- Free + Local > Cloud/SaaS philosophy established
+
+
+---
+
+## Pre-Compaction Summary - 2026-02-04 21:17 CST
+
+### Major Setup Completed Today
+
+#### 1. Identity & Names Established
+- **AI Name**: Kimi 🎙️
+- **User Name**: Rob
+- **Relationship**: Direct 1:1, private and trusted
+- **Deleted**: BOOTSTRAP.md (onboarding complete)
+
+#### 2. Bidirectional Voice System ✅
+- **Outbound**: Kokoro TTS @ `10.0.0.228:8880` with custom filenames
+- **Inbound**: Faster-Whisper (CPU, base model) for transcription
+- **Voice Filename Format**: `Kimi-YYYYMMDD-HHMMSS.ogg`
+- **Rule**: Voice in → Voice out, Text in → Text out
+- **No transcripts sent to Telegram** (internal transcription only)
+
+#### 3. Skills Created Today
+| Skill | Purpose | Location |
+|-------|---------|----------|
+| `local-whisper-stt` | Voice transcription (Faster-Whisper) | `/root/.openclaw/skills/local-whisper-stt/` |
+| `kimi-tts-custom` | Custom TTS filenames, voice-only mode | `/root/.openclaw/skills/kimi-tts-custom/` |
+| `qdrant-memory` | Vector memory augmentation | `/root/.openclaw/skills/qdrant-memory/` |
+
+#### 4. Qdrant Memory System
+- **Endpoint**: `http://10.0.0.40:6333` (local Proxmox LXC)
+- **Collection**: `openclaw_memories`
+- **Vector Size**: 768 (nomic-embed-text)
+- **Mode**: **Automatic** - stores/retrieves without prompting
+- **Architecture**: Hybrid (file-based + vector-based)
+- **Scripts**: store_memory.py, search_memories.py, hybrid_search.py, auto_memory.py
+
+#### 5. Cron Job Created
+- **Name**: monthly-backup-reminder
+- **Schedule**: First Monday of each month at 10:00 AM CST
+- **ID**: fb7081a9-8640-4c51-8ad3-9caa83b6ac9b
+- **Delivery**: Telegram message to Rob
+
+#### 6. Core Preferences Documented
+- **Accuracy**: Best quality, no compromises
+- **Performance**: Optimize for speed
+- **Research**: Always web search before installing
+- **Local Docs Exception**: OpenClaw/ClawHub docs prioritized
+- **Infrastructure**: Free > Paid, Local > Cloud, Private > Public
+- **Search Priority**: docs.openclaw.ai, clawhub.com, then other sources
+
+#### 7. Config Files Created/Updated
+- `USER.md` - Rob's profile
+- `IDENTITY.md` - Kimi's identity
+- `TOOLS.md` - Voice rules, search preferences, local services
+- `MEMORY.md` - Long-term curated memories
+- `AGENTS.md` - Installation policy, heartbeats
+- `openclaw.json` - TTS, skills, channels config
+
+### Next Steps (Deferred)
+- Continue with additional tool setup requests from Rob
+- Qdrant memory is in auto-mode, monitoring for important memories
+
+---
+
+## Lessons Learned - 2026-02-04 22:05 CST
+
+### Skill Script Paths
+**Mistake**: Tried to run scripts from wrong paths.
+**Correct paths**:
+- Whisper: `/root/.openclaw/workspace/skills/local-whisper-stt/scripts/transcribe.py`
+- TTS: `/root/.openclaw/workspace/skills/kimi-tts-custom/scripts/voice_reply.py`
+
+**voice_reply.py usage**:
+```bash
+python3 scripts/voice_reply.py <chat_id> "message text"
+# Example:
+python3 scripts/voice_reply.py 1544075739 "Hello there"
+```
+
+**Stored in Qdrant**: Yes (high importance, tags: voice,skills,paths,commands)

memory/2026-02-05.md

@@ -0,0 +1,195 @@
+# 2026-02-05 — Session Log
+
+## Major Accomplishments
+
+### 1. Knowledge Base System Created
+- **Collection**: `knowledge_base` in Qdrant (768-dim vectors, cosine distance)
+- **Purpose**: Personal knowledge repository organized by topic/domain
+- **Schema**: domain, path (hierarchy), subjects, category, content_type, title, checksum, source_url, date_scraped
+- **Content stored**: 
+  - docs.openclaw.ai (3 chunks)
+  - ollama.com/library (25 chunks)
+  - www.w3schools.com/python/ (7 chunks)
+  - Multiple list comprehension resources (3 entries)
+
+### 2. Smart Search Workflow Implemented
+- **Process**: Search KB first → Web search second → Synthesize → Store new findings
+- **Storage rules**: Only substantial content (>500 chars), unique (checksum), full attribution
+- **Auto-tagging**: date_scraped, source_url, domain detection
+- **Scripts**: `smart_search.py`, `kb_store.py`, `kb_review.py`, `scrape_to_kb.py`
+
+### 3. Monitoring System Established
+- **OpenClaw GitHub Repo Monitor**
+  - Schedule: Daily 11:00 AM
+  - Tracks: README, releases (5), issues (5)
+  - Relevance filter: Keywords affecting our setup (ollama, telegram, skills, memory, etc.)
+  - Notification: Only when significant changes detected (score ≥3 or high-priority areas)
+  - Initial finding: 24 high-priority areas affected
+
+- **Ollama Model Monitor**
+  - Schedule: Daily 11:50 AM
+  - Criteria: 100B+ parameter models only (to compete with gpt-oss:120b)
+  - Current large models: gpt-oss (120B), mixtral (8x22B = 176B effective)
+  - Notification: Only when NEW large models appear
+
+### 4. ACTIVE.md Syntax Library Created
+- **Purpose**: Pre-flight checklist to reduce tool usage errors
+- **Sections**: Per-tool validation (read, edit, write, exec, browser)
+- **Includes**: Parameter names, common mistakes, correct/wrong examples
+- **Updated**: AGENTS.md to require ACTIVE.md check before tool use
+
+## Key Lessons & Policy Changes
+
+### User Preferences Established
+1. **Always discuss before acting** — Never create/build without confirmation
+2. **100B+ models only** for Ollama monitoring (not smaller CPU-friendly models)
+3. **Silent operation** — Monitors only output when there's something significant to report
+4. **Exit code 0 always** for cron scripts (prevents "exec failed" logs)
+
+### Technical Lessons
+- `edit` tool requires `old_string` + `new_string` (not `newText`)
+- After 2-3 failed edit attempts, use `write` instead
+- Cron scripts must always `sys.exit(0)` — use output presence for signaling
+- `read` uses `file_path`, never `path`
+
+### Error Handling Policy
+- **Search-first strategy**: Check KB, then web search before fixing
+- **Exception**: Simple syntax errors (wrong param names, typos) — fix immediately
+
+## Infrastructure Updates
+
+### Qdrant Memory System
+- Hybrid approach: File-based + vector-based
+- Enhanced metadata: confidence, source, expiration, verification
+- Auto-storage triggers defined
+- Monthly review scheduled (cleanup of outdated entries)
+
+### Task Queue Repurposed
+- No longer for GPT delegation
+- Now for Kimi's own background tasks
+- GPT workloads moving to separate "Max" VM (future)
+
+## Active Cron Jobs
+| Time | Task | Channel |
+|------|------|---------|
+| 11:00 AM | OpenClaw repo check | Telegram (if significant) |
+| 11:50 AM | Ollama 100B+ models | Telegram (if new) |
+| 1st of month 3:00 AM | KB review (cleanup) | Silent |
+
+## Enforcement Milestone — 10:34 CST
+
+**Problem**: Despite updating AGENTS.md, TOOLS.md, and MEMORY.md with ACTIVE.md enforcement rules, I continued making the same errors:
+- Used `path` instead of `file_path` for `read`
+- Failed to provide `new_string` for `edit` (4+ consecutive failures)
+
+**Root Cause**: Documentation ≠ Behavior change. I wrote the rules but didn't follow them.
+
+**User Directive**: "Please enforce" — meaning actual behavioral change, not just file updates.
+
+**Demonstrated Recovery**:
+1. ✅ Used `read` with `file_path` correctly
+2. ❌ Failed `edit` 4 times (missing `new_string`)
+3. ✅ Switched to `write` per ACTIVE.md recovery protocol
+4. ✅ Successfully wrote complete file
+
+**Moving Forward**:
+- Pre-flight check BEFORE every tool call
+- Verify parameter names from ACTIVE.md
+- After 2 edit failures → use `write`
+- Quality over speed — no more rushing
+
+## Core Instruction Files Updated — 10:36 CST
+
+Updated all core .md files with enforced, actionable pre-flight steps:
+
+### TOOLS.md Changes:
+- Added numbered step-by-step pre-flight protocol
+- Added explicit instruction to read ACTIVE.md section for specific tool
+- Added parameter verification table with correct vs wrong parameters
+- Added emergency recovery rules table (edit fails → use write)
+- Added 5 critical reminders (file_path, old_string/new_string, etc.)
+
+### AGENTS.md Changes:
+- Added TOOLS.md to startup protocol (Step 3)
+- Added numbered steps for "Before Using Tools" section
+- Added explicit parameter verification table
+- Added emergency recovery section
+- Referenced TOOLS.md as primary enforcement location
+
+### Key Enforcement Chain:
+```
+AGENTS.md (startup) → TOOLS.md (pre-flight steps) → ACTIVE.md (tool-specific syntax)
+```
+
+## Knowledge Base Additions — Research Session
+
+**Stored to knowledge_base:** `ai/llm-agents/tool-calling/patterns`
+- **Title**: Industry Patterns for LLM Tool Usage Error Handling
+- **Content**: Research findings from LangChain, OpenAI, and academic papers on tool calling validation
+- **Key findings**:
+  - LangChain: handle_parsing_errors, retry mechanisms, circuit breakers
+  - OpenAI: strict=True, Structured Outputs API, Pydantic validation
+  - Multi-layer defense architecture (prompt → validation → retry → execution)
+  - Common failure modes: parameter hallucination, type mismatches, missing fields
+  - Research paper "Butterfly Effects in Toolchains" (2025): errors cascade through tool chains
+- **Our unique approach**: Pre-flight documentation checklist vs runtime validation
+
+---
+*Session type: Direct 1:1 with Rob*
+*Key files created/modified: ACTIVE.md, AGENTS.md, TOOLS.md, MEMORY.md, knowledge_base_schema.md, multiple monitoring scripts*
+*Enforcement activated: 2026-02-05 10:34 CST*
+*Core files updated: 2026-02-05 10:36 CST*
+
+## Max Configuration Update — 23:47 CST
+
+**Max Setup Differences from Initial Design:**
+- **Model**: minimax-m2.1:cloud (switched from GPT-OSS)
+- **TTS Skill**: max-tts-custom (not kimi-tts-custom)
+- **Filename format**: Max-YYYYMMDD-HHMMSS.ogg
+- **Voice**: af_bella @ Kokoro 10.0.0.228:8880
+- **Shared Qdrant**: Both Kimi and Max use same Qdrant @ 10.0.0.40:6333
+  - Collections: openclaw_memories, knowledge_base
+- **TOOLS.md**: Max updated to match comprehensive format with detailed tool examples, search priorities, Qdrant scripts
+
+**Kimi Sync Options:**
+- Stay on kimi-k2.5:cloud OR switch to minimax-m2.1:cloud
+- IDENTITY.md model reference already accurate for kimi-k2.5
+
+## Evening Session — 19:55-22:45 CST
+
+### Smart Search Fixed
+- Changed default `--min-kb-score` from 0.7 to 0.5
+- Removed server-side `score_threshold` (too aggressive)
+- Now correctly finds KB matches (test: 5 results for "telegram dmPolicy")
+- Client-side filtering shows all results then filters
+
+### User Preferences Reinforced
+- **Concise chats only** — less context, shorter replies
+- **Plain text in Telegram** — no markdown formatting, no bullet lists with symbols
+- **One step at a time** — wait for response before proceeding
+
+### OpenClaw News Search
+Searched web for today's OpenClaw articles. Key findings:
+- Security: CVE-2026-25253 RCE bug patched in v2026.1.29
+- China issued security warning about improper deployment risks
+- 341 malicious ClawHub skills found stealing data
+- Trend: Viral adoption alongside security crisis
+
+### GUI Installation Started on Deb
+- Purpose: Enable Chrome extension for OpenClaw browser control
+- Packages: XFCE4 desktop, Chromium browser, LightDM
+- Access: Proxmox console (no VNC needed)
+- Status: Complete — 267 packages installed
+- Next: Configure display manager, launch desktop, install OpenClaw extension
+
+### OpenClaw Chrome Extension Installation Method
+**Discovery**: Extension is NOT downloaded from Chrome Web Store
+**Method**: Installed via OpenClaw CLI command
+**Steps**:
+1. Run `openclaw browser extension install` (installs to ~/.openclaw/browser-extension/)
+2. Open Chromium → chrome://extensions/
+3. Enable "Developer mode" (toggle top right)
+4. Click "Load unpacked"
+5. Select the extension path shown after install
+6. Click OpenClaw toolbar button to attach to tab
+**Alternative**: Clone from GitHub and load browser-extension/ folder directly

memory/2026-02-06.md

@@ -0,0 +1,78 @@
+# 2026-02-06 — Daily Memory Log
+
+## Operational Rules Updated
+
+### Notification Rules (from Rob)
+- Always use Telegram text only unless requested otherwise
+- Only send notifications between 7am-10pm CST
+- All timestamps and time usage must be US CST (including Redis)
+- If notification needed outside hours, queue as heartbeat task to send at next allowed time
+- Stored in Qdrant: IDs 83a98a6e-058f-4c2f-91f4-001d5a18acba, 8729ba36-93a1-4cc2-90b0-00bd22bf19b1
+- Updated HEARTBEAT.md with Task #3: Send Delayed Notifications
+
+## Research Completed
+
+### Ollama Pricing: Max vs Pro Plans
+**Source:** https://ollama.com/pricing
+
+| Plan | Price | Key Features |
+|------|-------|--------------|
+| Free | $0 | Local models only, unlimited public models |
+| Pro | $20/mo | Multiple cloud models, more usage, 3 private models, 3 collaborators |
+| Max | $100/mo | 5+ cloud models, 5x usage vs Pro, 5 private models, 5 collaborators |
+
+**Key Differences:**
+- Concurrency: Pro = multiple, Max = 5+ models
+- Cloud usage: Max = 5x Pro allowance
+- Private models: Pro = 3, Max = 5
+- Collaborators per model: Pro = 3, Max = 5
+
+Stored in KB (Ollama/Pricing domain).
+
+## New Project Ideas
+
+### 3rd OpenClaw LXC
+- Rob wants to setup a 3rd OpenClaw LXC
+- Clone of Max's setup
+- Will run local GPT
+- Status: Idea phase, awaiting planning/implementation
+
+## Agent Collaboration
+
+- Sent notification rules to Max via agent-messages stream
+- Max informed of all operational updates
+
+### Full Search Definition (from Rob)
+- When Rob says "full search": use ALL tools available, find quality results
+- Combine SearXNG, KB search, web crawling, and any other resources
+- Do not limit to one method—comprehensive, high-quality information
+- Stored in Qdrant: ID bb4a465a-3c6e-48a8-d8c-52da5b1fdf48
+
+### Shorthand Terms
+- **msgs** = Redis messages (agent-messages stream at 10.0.0.36:6379)
+  - Shortcut for checking/retrieving agent messages between Kimi and Max
+  - Stored in Qdrant: ID e5e93700-b04b-4db4-9c4b-d6b94166be7f
+- **messages** = Telegram direct chat (conversational)
+- **notification** = Telegram alerts/updates (one-way notifications)
+  - Stored in Qdrant: ID e88ec7ea-9d77-45c3-8057-cb7a54077060
+
+### Rob's Personality & Style
+- Comical and funny most of the time
+- Humor is logical/structured (not random/absurd)
+- Has fun with the process
+- Applies to content creation and general approach
+- Stored in Qdrant: ID b58defd6-e8fc-4420-b75c-aefd4720e70d
+
+### YouTube SEO - Tags Format
+- Target: ~490 characters of comma-separated tags
+- Include: primary keywords, secondary keywords, long-tail terms
+- Mix: broad terms (Homelab) + specific terms (Proxmox LXC)
+- Example stored in Qdrant: ID 8aa534f3-6e3f-49d9-ae5f-803ff9e80121
+
+### YouTube SEO - Research Rule
+- **CRITICAL:** Pull latest 48 hours of search data/trends when composing SEO elements
+- Current data > general keywords for best search results
+- Stored in Qdrant: ID bbe76456-01b5-48b5-9c0b-dd8c06680e82
+
+---
+*Stored for long-term memory retention*

memory/2026-02-07.md

@@ -0,0 +1,72 @@
+# 2026-02-07 — Daily Memory Log
+
+## Agent System Updates
+
+### Jarvis (Local Agent) Setup
+- Jarvis deployed as local LLM clone of Max
+- 64k context window (sufficient for most tasks)
+- Identity: "jarvis" in agent-messages stream
+- Runs on CPU (no GPU)
+- Requires detailed step-by-step instructions
+- One command per step with acknowledgements required
+- Conversational communication style expected
+
+### Multi-Agent Protocols Established
+- SSH Host Change Protocol: Any agent modifying deb/deb2 must notify others via agent-messages
+- Jarvis Task Protocol: All steps provided upfront, execute one at a time with ACKs
+- Software Inventory Protocol: Check installed list before recommending
+- Agent messaging via Redis stream at 10.0.0.36:6379
+
+### SOUL.md Updates (All Agents)
+- Core Truths: "Know the roster", "Follow Instructions Precisely"
+- Communication Rules: Voice/text protocols, no filler words
+- Infrastructure Philosophy: Privacy > convenience, Local > cloud, Free > paid
+- Task Handling: Acknowledge receipt, report progress, confirm completion
+
+## Infrastructure Changes
+
+### SSH Hosts
+- **deb** (10.0.0.38): OpenClaw removed, now available for other uses
+- **deb2** (10.0.0.39): New host added, same credentials (n8n/passw0rd)
+
+### Software Inventory (Never Recommend These)
+- n8n, ollama, openclaw, openwebui, anythingllm
+- searxng, flowise
+- plex, radarr, sonarr, sabnzbd
+- comfyui
+
+## Active Tasks
+
+### Jarvis KB Documentation Task
+- 13 software packages to document:
+  1. n8n, 2. ollama, 3. openwebui, 4. anythingllm, 5. searxng
+  6. flowise, 7. plex, 8. radarr, 9. sonarr, 10. sabnzbd
+  11. comfyui, 12. openclaw (GitHub), 13. openclaw (Docs)
+- Status: Task assigned, awaiting Step 1 completion report
+- Method: Use batch_crawl.py or scrape_to_kb.py
+- Store with domain="Software", path="<name>/Docs"
+
+### Jarvis Tool Verification
+- Checking for: Redis scripts, Python client, Qdrant memory scripts
+- Whisper STT, TTS, basic tools (curl, ssh)
+- Status: Checklist sent, awaiting response
+
+### Jarvis Model Info Request
+- Requested: Model name, hardware specs, 64k context assessment
+- Status: Partial response received (truncated), may need follow-up
+
+## Coordination Notes
+
+- All agents must ACK protocol messages
+- Heartbeat checks every 30 minutes
+- Agent-messages stream monitored for new messages
+- Delayed notifications queue for outside 7am-10pm window
+- All timestamps use US CST
+
+## Memory Storage
+- 19 new memories stored in Qdrant today
+- Includes protocols, inventory, Jarvis requirements, infrastructure updates
+- All tagged for semantic search
+
+---
+*Stored for long-term memory retention*

memory/2026-02-08.md

@@ -0,0 +1,53 @@
+# 2026-02-08 — Daily Memory Log
+
+## Session Start
+- **Date:** 2026-02-08
+- **Agent:** Kimi
+
+## Bug Fixes & Improvements
+
+### 1. Created Missing `agent_check.py` Script
+- **Location:** `/skills/qdrant-memory/scripts/agent_check.py`
+- **Purpose:** Check agent messages from Redis stream
+- **Features:**
+  - `--list N` — List last N messages
+  - `--check` — Check for new messages since last check
+  - `--last-minutes M` — Check messages from last M minutes
+  - `--mark-read` — Update last check timestamp
+- **Status:** ✅ Working — tested and functional
+
+### 2. Created `create_daily_memory.py` Script
+- **Location:** `/skills/qdrant-memory/scripts/create_daily_memory.py`
+- **Purpose:** Create daily memory log files automatically
+- **Status:** ✅ Working — created 2026-02-08.md
+
+### 3. Fixed `scrape_to_kb.py` Usage
+- **Issue:** Used `--domain`, `--path`, `--timeout` flags (wrong syntax)
+- **Fix:** Used positional arguments: `url domain path`
+- **Result:** Successfully scraped all 13 software docs
+
+### 4. SABnzbd Connection Fallback
+- **Issue:** sabnzbd.org/wiki/ returned connection refused
+- **Fix:** Used GitHub repo (github.com/sabnzbd/sabnzbd) as fallback
+- **Result:** ✅ 4 chunks stored from GitHub README
+
+### 5. Embedded Session Tool Issues (Documented)
+- **Issue:** Embedded sessions using `path` instead of `file_path` for `read` tool
+- **Note:** This is in OpenClaw gateway/embedded session code — requires upstream fix
+- **Workaround:** Always use `file_path` in workspace scripts
+
+## KB Documentation Task Completed
+All 13 software packages documented in knowledge_base (64 total chunks):
+- n8n (9), ollama (1), openwebui (7), anythingllm (2)
+- searxng (3), flowise (2), plex (13), radarr (1)
+- sonarr (1), sabnzbd (4), comfyui (2)
+- openclaw GitHub (16), openclaw Docs (3)
+
+## Activities
+
+*(Log activities, decisions, and important context here)*
+
+## Notes
+
+---
+*Stored for long-term memory retention*

memory/2026-02-09.md

@@ -0,0 +1,42 @@
+# 2026-02-09 — Daily Log
+
+## System Fixes & Setup
+
+### 1. Fixed pytz Missing Dependency
+- **Issue:** Heartbeat cron jobs failing with `ModuleNotFoundError: No module named 'pytz'`
+- **Fix:** `pip install pytz`
+- **Result:** All heartbeat checks now working (agent messages, timestamp logging, delayed notifications)
+
+### 2. Created Log Monitor Skill
+- **Location:** `/root/.openclaw/workspace/skills/log-monitor/`
+- **Purpose:** Daily automated log scanning and error repair
+- **Schedule:** 2:00 AM CST daily via system crontab
+- **Features:**
+  - Scans systemd journal, cron logs, OpenClaw session logs
+  - Auto-fixes: missing Python modules, permission issues, service restarts
+  - Alerts on: disk full, services down, unknown errors
+  - Comprehensive noise filtering (NVIDIA, PAM, rsyslog container errors)
+  - Self-filtering (excludes its own logs, my thinking blocks, tool errors)
+  - Service health check: Redis via Python (redis-cli not in container)
+- **Report:** `/tmp/log_monitor_report.txt`
+
+### 3. Enabled Parallel Tool Calls
+- **Configuration:** Ollama `parallel = 8`
+- **Usage:** All independent tool calls now batched and executed simultaneously
+- **Tested:** 8 parallel service health checks (Redis, Qdrant, Ollama, SearXNG, Kokoro TTS, etc.)
+- **Previous:** Sequential execution (one at a time)
+
+### 4. Redis Detection Fix
+- **Issue:** `redis-cli` not available in container → false "redis-down" alerts
+- **Fix:** Use Python `redis` module for health checks
+- **Status:** Redis at 10.0.0.36:6379 confirmed working
+
+## Files Modified/Created
+- `/root/.openclaw/workspace/skills/log-monitor/scripts/log_monitor.py` (new)
+- `/root/.openclaw/workspace/skills/log-monitor/SKILL.md` (new)
+- System crontab: Added daily log monitor job
+
+## Notes
+- Container has no GPU → NVIDIA module errors are normal (filtered)
+- rsyslog kernel log access denied in container (filtered)
+- All container-specific "errors" are now excluded from reports

memory/2026-02-10.md

@@ -0,0 +1,157 @@
+# 2026-02-10 — Daily Memory Log
+
+## Qdrant Memory System — Manual Mode
+
+**Major change:** Qdrant memory now MANUAL ONLY.
+
+Two distinct systems established:
+- **"remember this" or "note"** → File-based (daily logs + MEMORY.md) — automatic, original design
+- **"q remember", "q recall", "q save", "q update"** → Qdrant `kimi_memories` — manual, only when "q" prefix used
+
+**Commands:**
+- "q remember" = store one item to Qdrant
+- "q recall" = search Qdrant  
+- "q save" = store specific item
+- "q update" = bulk sync all file memories to Qdrant without duplicates
+
+## Redis Messaging — Manual Mode
+
+**Change:** Redis agent messaging now MANUAL ONLY.
+
+- No automatic heartbeat checks for Max's messages
+- No auto-notification queue processing
+- Only manual when explicitly requested: "check messages" or "send to Max"
+
+## New Qdrant Collection: kimi_memories
+
+**Created:** `kimi_memories` collection at 10.0.0.40:6333
+- Vector size: 1024 (snowflake-arctic-embed2)
+- Distance: Cosine
+- Model: snowflake-arctic-embed2 pulled to 10.0.0.10 (GPU)
+- Purpose: Manual memory backup when requested
+
+## Critical Lesson: Immediate Error Reporting
+
+**Rule established:** When hitting a blocking error during an active task, report IMMEDIATELY — don't wait for user to ask.
+
+**What I did wrong:**
+- Said "let me know when it's complete" for "q save ALL memories"
+- Discovered Qdrant was unreachable (host down)
+- Stayed silent instead of immediately reporting
+- User had to ask for status to discover I was blocked
+
+**Correct behavior:**
+- Hit blocking error → immediately report: "Stopped — [reason]. Cannot proceed."
+- Never imply progress is happening when it's not
+- Applies to: service outages, permission errors, resource exhaustion
+
+## Memory Backup Success
+
+**Completed:** "q save ALL memories" — 39 comprehensive memories successfully backed up to `kimi_memories` collection.
+
+**Contents stored:**
+- Identity & personality
+- Communication rules  
+- Tool usage rules
+- Infrastructure details
+- YouTube SEO rules
+- Setup milestones
+- Boundaries & helpfulness principles
+
+**Collection status:**
+- Name: `kimi_memories`
+- Location: 10.0.0.40:6333
+- Vectors: 39 points
+- Model: snowflake-arctic-embed2 (1024 dims)
+
+## New Qdrant Collection: kimi_kb
+
+**Created:** `kimi_kb` collection at 10.0.0.40:6333
+- Vector size: 1024 (snowflake-arctic-embed2)
+- Distance: Cosine
+- Purpose: Knowledge base storage (web search, documents, data)
+- Mode: Manual only — no automatic storage
+
+**Scripts:**
+- `kb_store.py` — Store web/docs to KB with metadata
+- `kb_search.py` — Search knowledge base with domain filtering
+
+**Usage:**
+```bash
+# Store to KB
+python3 kb_store.py "Content" --title "X" --domain "Docker" --tags "container"
+
+# Search KB
+python3 kb_search.py "docker volumes" --domain "Docker"
+```
+
+**Test:** Successfully stored and retrieved Docker container info.
+
+## Unified Search: Perplexity + SearXNG
+
+**Architecture:** Perplexity primary, SearXNG fallback
+
+**Primary:** Perplexity API (AI-curated, ~$0.005/query)  
+**Fallback:** SearXNG local (privacy-focused, free)
+
+**Commands:**
+```bash
+search "your query"        # Perplexity → SearXNG fallback
+search p "your query"      # Perplexity only
+search local "your query"  # SearXNG only
+search --citations "query" # Include source links
+search --model sonar-pro "query" # Pro model for complex tasks
+```
+
+**Models:**
+- `sonar` — Quick answers (default)
+- `sonar-pro` — Complex queries, coding
+- `sonar-reasoning` — Step-by-step reasoning
+- `sonar-deep-research` — Comprehensive research
+
+**Test:** Successfully searched "top 5 models used with openclaw" — returned Claude Opus 4.5, Sonnet 4, Gemini 3 Pro, Kimi K 2.5, GPT-4o with citations.
+
+## Perplexity API Setup
+
+**Configured:** Perplexity API skill created at `/skills/perplexity/`
+
+**Details:**
+- Key: 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
+- Endpoint: https://api.perplexity.ai/chat/completions
+- Models: sonar, sonar-pro, sonar-reasoning, sonar-deep-research
+- Format: OpenAI-compatible, ~$0.005 per query
+
+**Usage:** See "Unified Search" section above for primary usage. Direct API access:
+```bash
+python3 skills/perplexity/scripts/query.py "Your question" --citations
+```
+
+**Note:** Perplexity sends queries to cloud servers. Use `search local "query"` for privacy-sensitive searches.
+
+## Sub-Agent Setup (Option B)
+
+**Configured:** Sub-agent defaults pointing to .10 Ollama
+
+**Config changes:**
+- `agents.defaults.subagents.model`: `ollama-remote/qwen3:30b-a3b-instruct-2507-q8_0`
+- `models.providers.ollama-remote`: Points to `http://10.0.0.10:11434/v1`
+- `tools.subagents.tools.deny`: write, edit, apply_patch, browser, cron (safer defaults)
+
+**What it does:**
+- Spawns background tasks on qwen3:30b at .10
+- Inherits main agent context but runs inference remotely
+- Auto-announces results back to requester chat
+- Max 2 concurrent sub-agents
+
+**Usage:**
+```
+sessions_spawn({
+  task: "Analyze these files...",
+  label: "Background analysis"
+})
+```
+
+**Status:** Configured and ready
+
+---
+*Stored for long-term memory retention*

memory/heartbeat-timestamps.txt

@@ -0,0 +1 @@
+2026-02-10T11:58:48-06:00