Self-Hosted Bookmarks That Tag Themselves With Local AI
A bookmark folder is where links go to die. Give it a local-AI librarian.
Load-Balance a Multi-Node Ollama Cluster With Olla
Three Ollama boxes, one smart endpoint that routes, fails over, and reports.
Build a Read-Only Homelab MCP Server for Your LLM
Let an AI read your cluster's health and metrics — and change nothing.
Give Your Local AI Private Web Search With SearXNG
Your offline LLM can't see today. Wire it to your own search engine.
Proxmox GPU passthrough: give one VM the whole card
One VM gets the card; the host gives up control.
Point the Homelab Tools at Any Model — Including One You Host
Four of my eleven tools didn't work on my own website.
RAG for Your Homelab Wiki: Answers That Cite Their Source
Your wiki answers questions now — and cites where it read them.
Track AI Token Spend in Grafana: Claude, Codex, and Ollama
Every token your AI tools burn, graphed next to your CPU temps.
10 Mistakes I Made Building a Homelab Second Brain (And How Each Got Fixed)
Ten ways I broke my second brain so yours stays whole.
Make Your AI Agents Read the Docs First, Every Time
Agents that read the docs first, every session, provably current.
Semantic Search for Your Notes, Running Locally
Semantic search over your notes, no cloud, no API key.
Open WebUI Advanced: RAG, Pipelines, and Custom System Prompts
Open WebUI past the chat box: RAG, pipelines, and prompts.
Hermes Agent: Self-Hosted AI Agent with Fallback Model Chains
A self-hosted agent with a fallback chain for bad model days.
CPU-Only Ollama Cluster on Proxmox LXC: 3-Node Setup with Load Balancing
Three CPU-only nodes serving local LLMs behind one endpoint.