Skip to content
Infrastructure

Homelab

24 self-hosted services, 80+ automated workflows, and a local AI stack. All running on-premise. No cloud dependencies, no third-party data processing.

Architecture

Capture
Omi Wearable reMarkable RSS Feeds Oura Ring Documents
Processing
n8n (80+ workflows) LM Studio (local LLM) WhisperX (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

20+ Docker containers

AI Processing

Windows PC

Ryzen 5 5600X, 32 GB RAM, RTX 4060

LM Studio, WhisperX, 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: 80+ workflows handling integrations, pipelines, and scheduled tasks

Home Assistant HA Green

Smart home control with voice satellites and device automation

LM Studio Windows PC

Local LLM inference (Qwen3.5 9B) with OpenAI-compatible API

WhisperX Windows PC

GPU-accelerated speech-to-text with speaker diarization for transcription pipelines

Ollama Windows PC

Secondary LLM backend for model evaluation and testing

AnythingLLM TrueNAS

RAG interface for querying documents with conversational search (384-dim embeddings)

Qdrant TrueNAS

Vector database powering semantic search across all stored content (384 dimensions)

Paperless-ngx TrueNAS

Document ingestion with OCR, tagging, and full-text search

BookStack TrueNAS

Internal wiki for journals, runbooks, and reference documentation

Obsidian MacBook Pro

Primary note-taking and knowledge management via Markdown

FreshRSS TrueNAS

RSS aggregation with AI-scored relevance filtering

Linkwarden TrueNAS

Bookmark manager with full-text archival and tagging

Plex TrueNAS

Media server for movies, TV, and music libraries

Immich TrueNAS

Self-hosted photo management with facial recognition and search

Vaultwarden TrueNAS

Bitwarden-compatible password manager, fully self-hosted

WireGuard TrueNAS

VPN for secure remote access to all internal services

Cloudflared TrueNAS

Cloudflare tunnels for externally exposed services

Uptime Kuma TrueNAS

Service health monitoring with alerting via ntfy

Netdata TrueNAS

Real-time system metrics: CPU, RAM, disk, and network

ntfy TrueNAS

Push notification hub for all automated alerts

Stirling-PDF TrueNAS

Local PDF processing: merge, split, convert, OCR

Syncthing TrueNAS

File sync across reMarkable, Obsidian vault, and workstations

RustDesk TrueNAS

Self-hosted remote desktop access

Actual Budget TrueNAS

Privacy-first budgeting and financial tracking

Automation Highlights

80+ n8n workflows handle recurring tasks, data pipelines, and infrastructure maintenance.

Morning Briefing

Daily summary delivered by email: weather, calendar, tasks, and Oura ring sleep data, generated by the local LLM.

Transcription Pipeline

Omi wearable captures conversations, WhisperX transcribes locally with speaker diarization, n8n classifies content and routes action items to Todoist.

Personal Knowledge Management Pipeline

Notes from Obsidian, scans from reMarkable, and documents from Paperless are processed, embedded, and indexed for semantic search.

Self-Healing Infrastructure

Downtime triggers AI triage, automatic restart attempts, and rollback if health checks fail. Alerts sent via ntfy.

Docker Update Pipeline

Weekly automated container updates with pre-update snapshots, health checks, and automatic rollback on failure.

RSS AI Digest

FreshRSS feeds scored by relevance, top articles summarized by the LLM, and a daily digest pushed to ntfy.

AI Stack

Local LLM Inference

LM Studio serves Qwen3.5 9B on an RTX 4060 via an OpenAI-compatible API. All AI workflows (classification, summarization, briefings) route through this single endpoint.

LM Studio Qwen3.5 9B RTX 4060

RAG & Semantic Search

Documents, notes, and scans are embedded into Qdrant (384-dim vectors). AnythingLLM provides a conversational interface for querying the full knowledge base.

Qdrant AnythingLLM 384-dim vectors

Speech-to-Text

WhisperX on the GPU handles transcription with speaker diarization for the Omi wearable and Home Assistant voice satellites. All processing stays local.

WhisperX CUDA Speaker Diarization
24 Services
80+ Workflows
3 Servers
0 Cloud Dependencies