Infrastructure

Homelab

A privacy-first, self-hosted infrastructure running 24 services across 3 servers. All data processed locally with zero cloud dependencies for core functionality.

Architecture

Capture
Omi Wearable reMarkable RSS Feeds Oura Ring Documents
Processing
n8n (80+ workflows) LM Studio (local LLM) Whisper (speech-to-text) Paperless (OCR)
Knowledge
BookStack (wiki) Obsidian (notes) Qdrant (vectors) AnythingLLM (RAG)

Hardware

NAS / Docker Host

TerraMaster F2-424

16 GB RAM, ZFS (500 GB mirror + 8 TB RAIDZ)

20+ Docker containers

AI Processing

Windows PC

Ryzen 5 5600X, 32 GB RAM, RTX 4060

LM Studio, Whisper, Ollama

Home Automation

Home Assistant Green

Dedicated HA appliance

Home Assistant + voice satellites

Daily Driver

MacBook Pro

Development, Obsidian sync

Obsidian REST API

Services (24)

Automation2AI5Knowledge5Media2Security3Monitoring3Tools4
n8n TrueNAS

Workflow automation platform with 80+ active workflows

Home Assistant HA Green

Smart home control with voice satellites and contextual automations

LM Studio Windows PC

Local LLM inference server (Qwen3 8B) — powers all AI workflows

Whisper Windows PC

GPU-accelerated speech-to-text transcription

Ollama Windows PC

Alternative LLM backend running alongside LM Studio

AnythingLLM TrueNAS

RAG search across all documents with vector embeddings

Qdrant TrueNAS

Vector database for semantic search across knowledge base

Paperless-ngx TrueNAS

Document OCR, classification, and archival

BookStack TrueNAS

Structured wiki — auto-updated daily journals and weekly summaries

Obsidian MacBook Pro

Personal notes and daily journals with REST API for automation

FreshRSS TrueNAS

RSS reader with AI-powered article scoring and digests

Linkwarden TrueNAS

Self-hosted bookmark manager

Plex TrueNAS

Media server for movies, TV, and music

Immich TrueNAS

Self-hosted photo management with ML-powered organization

Vaultwarden TrueNAS

Self-hosted Bitwarden-compatible password manager

WireGuard TrueNAS

VPN for secure remote access to all services

Cloudflared TrueNAS

Secure tunnels for external service access

Uptime Kuma TrueNAS

Service health monitoring with alerting

Netdata TrueNAS

Real-time system performance metrics

ntfy TrueNAS

Push notification hub for all automations

Stirling-PDF TrueNAS

Self-hosted PDF manipulation toolkit

Syncthing TrueNAS

File sync between devices — reMarkable, Obsidian vault

RustDesk TrueNAS

Self-hosted remote desktop access

Actual Budget TrueNAS

Privacy-first budgeting and financial tracking

Automation Highlights

80+ n8n workflows handle everything from morning briefings to infrastructure self-healing. All AI processing runs locally via LM Studio on an RTX 4060.

Morning Briefing

AI-generated daily briefing with weather, tasks, calendar, and health data — delivered via email and voice

Omi Pipeline

Wearable captures conversations, transcribes locally via Whisper, classifies by context, extracts action items to Todoist

PKM Pipeline

Documents from Obsidian, reMarkable, and Paperless are processed, embedded, and routed to BookStack and vector search

Self-Healing Infrastructure

AI-powered triage of service failures with auto-restart, health checks, and rollback

Docker Update Pipeline

Weekly container update checks with safe rollout — pre-backup, health check, and auto-rollback on failure

RSS AI Digest

Daily AI-curated news digest — articles scored by relevance, top picks summarized and pushed via notification

AI Stack

Local LLM Inference

LM Studio serves Qwen3 8B via an OpenAI-compatible API. Every AI-powered workflow — from document classification to morning briefings — runs against this single local endpoint. No data leaves the network.

LM Studio Qwen3 8B RTX 4060

RAG & Semantic Search

Documents from Obsidian, BookStack, and Paperless are embedded into Qdrant vector collections. AnythingLLM provides conversational search across all knowledge sources.

Qdrant AnythingLLM 384-dim vectors

Speech-to-Text

Faster-Whisper runs GPU-accelerated on the RTX 4060, transcribing audio from the Omi wearable and voice satellites in real-time.

Whisper CUDA Ollama
24 Services
80+ Workflows
3 Servers
0 Cloud Dependencies