Self-Hosted · Privacy-First · Local AI

Built to run
entirely
on our own.

A private homelab running local AI, self-hosted services, and full-stack infrastructure — no cloud subscriptions, no data leaving the premises.

80k+ Photos archived
64 GB Local VRAM
100% Self-hosted
scroll

Local AI

Inference, generation,
and retrieval — on premise.

All AI workloads run on dedicated hardware with AMD Radeon GPUs. No API calls to third-party services. No data shared externally.

// LLM

Language Models

Ollama serves large language models locally on two dedicated AI servers. Each family member gets their own isolated instance and knowledge base.

Ollama Open WebUI AMD ROCm
// RAG

Knowledge Retrieval

Documents from Nextcloud are automatically synced and indexed into per-user vector databases. Web articles are captured via a custom Chrome extension.

Qdrant nomic-embed-text RAG
// VISION

Image Generation

ComfyUI runs on a dedicated machine with an NVIDIA RTX 5060 Ti, handling image generation workflows independently from the language model servers.

ComfyUI RTX 5060 Ti NVIDIA
// AGENT

Conversational Agents

Custom AI agents with persistent memory run on local LLMs and integrate with messaging platforms, enabling fully private, always-on assistants.

OpenClaw WhatsApp Qwen3

Infrastructure

Every service
runs at home.

A complete self-hosted stack covering productivity, security, storage, and communication — for the whole family.

// STORAGE

Files & Collaboration

Nextcloud with OnlyOffice handles documents, calendars, and contacts across all devices. Files are stored on local NAS hardware, not in any cloud.

Nextcloud OnlyOffice NFS/NAS
// PHOTOS

Photo Archive

Over 80,000 photos managed by Immich with AI-powered face recognition, smart search, and automatic album generation — all running locally.

Immich CLIP PostgreSQL
// SECURITY

Passwords & Identity

Vaultwarden — a self-hosted Bitwarden-compatible server — manages credentials for the entire family across all platforms and devices.

Vaultwarden Bitwarden clients
// MAIL

Email Infrastructure

A full mail stack with external relay servers in the USA and an internal Mailcow instance. Full SPF, DKIM, and DMARC configuration with spam filtering.

Mailcow Postfix DMARC

Full Stack

The complete
technology stack.

Every layer of the infrastructure, from hardware to application.

compute AI Servers (×3) Intel Core i5-14600KF / i5-14400F, AMD Radeon R9700 32 GB, NVIDIA RTX 5060 Ti 16 GB
storage NAS (×2) 2×2 TB SATA per unit — primary NFS share and Restic backup target
virtualisation KVM Hosts (×2) AMD Ryzen 7 8845HS / Intel i5-12450H running all internal VMs
os Ubuntu 24.04 LTS All virtual machines and servers — 64-bit, managed via Ansible
automation Ansible + Semaphore All deployments, updates, and configuration changes via playbooks
networking WireGuard VPN Secure tunnel between external servers and internal network
firewall Shorewall Iptables frontend on all externally-facing servers, strict DROP policy
dns / filter Pi-hole (×2) Network-wide DNS filtering and ad blocking, redundant setup
monitoring Grafana + Prometheus Node Exporter on all servers, centralised alerting via email
backup Restic Incremental, encrypted, deduplicated backups to local NAS — daily
proxy / ssl Nginx + Let's Encrypt Reverse proxy for all services, automated certificate renewal
containers Docker All services run in Docker Compose — isolated, reproducible deployments

Philosophy

Why we run
everything ourselves.

These are not decisions made for technical novelty. They are deliberate choices about privacy, ownership, and independence.

01

Data stays home

Photos, documents, conversations, and passwords never leave our infrastructure. No third-party analytics, no telemetry, no cloud sync.

02

No subscriptions

We deliberately chose not to rely on Microsoft 365, iCloud, Google Workspace, or any commercial AI API as a dependency for daily life.

03

AI without compromise

Local LLMs are capable enough for everyday use. Sensitive queries never need to leave the building to reach an intelligence that can help.

04

Managed as code

Every server configuration is version-controlled and deployable from scratch. Nothing is configured manually that cannot be reproduced automatically.