Home Lab AI Operator
Run a multi-node local AI lab on hardware you already own. 9 production-proven skills covering the whole operator stack: fit models to GPU VRAM before you download, squeeze 100% residency with the Ollama fit optimizer, route tasks across local nodes and cloud tiers, serve with llama-server, run the right workload on the right box, train on consumer GPUs, keep it all alive with health watchdogs and process reaping, and bring dead PCs back over LAN with PXE repair. Every procedure measured on a real multi-node lab — mixed NVIDIA and AMD consumer GPUs.
Works with every agent that reads SKILL.md — Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, and more.
One payment, lifetime access. 7 skills unlock instantly in your library.
30-day refund guarantee
Instant unlock in your library
Free updates from the creator
What's included
7 skills
Deploy zero-dependency watchdogs to catch and alert on automation failures in real-time.
Production-grade playbook for serving, fitting, and verifying llama.cpp llama-server on multi-GPU Linux systems.
Automated LLM fine-tuning orchestration with hardware probing and specific dependency management for homelabs.
Manage the full local LLM lifecycle: optimize VRAM fit, deploy secure LAN-served apps, and orchestrate GPU training.
Tune Ollama models for 100% VRAM residency and peak throughput by finding the exact zero-spill layer and context limits.
Boot and repair dead Windows machines over the network using PXE, iPXE, and remote Linux rescue environments.
Orchestrate PXE-based Windows repair and recovery environments via iPXE, WinPE, and Linux rescue tools.
See it in action
automation health monitoring
Example session with this skill installed
My content pipeline stopped working three days ago and I just realized it today. Set up a watchdog so this never happens again.
- Read your context and instructions
- Compiled the automation health monitoring
I have implemented a high-frequency watchdog to monitor your content pipeline. I migrated the monitoring logic to a standard-library Python script to ensure it remains functional even if your pipeline's virtual environment breaks, and configured it to alert your Telegram channel immediately upon failure.
Automation Monitoring Implementation
| Component | Action Taken | Configuration |
|---|---|---|
| Watchdog Script | Created unified_health_watchdog.py | Python stdlib, no external deps |
| Cron Schedule | Initialized no_agent cron | */20 * * * * (Every 20 mins) |
| Alerting | Linked to TELEGRAM_HOME_CHANNEL | Immediate paging, 1/day dedupe |
| Failure Detection | Log scanning + Cron state check | Searches for exit status 1 and FAIL |
| Legacy Cleanup | Paused daily_summary_bot | Prevents redundant alerts |
# Unified Watchdog Wrapper (~/.agent-home/scripts/unified_health_watchdog.sh)
#!/bin/bash
export $(grep -v '^#' ~/.agent-home/.env | xargs)
python3 ~/.agent-home/scripts/unified_health_watchdog.py --check content-pipeline
Next steps
- Send a test message via the Telegram bot to verify the connection.
- Intentionally trigger a script error in a staging task to confirm the 20-minute alert cycle.
- Review
~/.agent-home/scripts/.unified_watchdog_state.jsontomorrow to ensure deduplication is working.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every skill in this bundle passes our trust checks.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back