Self-Host Everything.
Own Your Data.
Technical guides and reference documentation for Docker, Linux, and local AI. From Nextcloud to Ollama — practical step-by-step instructions to run it on your own hardware.
services: ollama: image: ollama/ollama:latest ports: ["11434:11434"] volumes: [./ollama:/root/.ollama] open-webui: image: ghcr.io/open-webui/open-webui ports: ["3000:8080"] # → http://localhost:3000
Popular Self-Hosting Architectures
Direct reference setups for personal cloud, local AI, and networking.
Core Pillar Architectures
Foundation guides and reference architectures for homelab deployments.
Setting Up RustDesk Self-Hosted Server with HTTPS on Docker
Deploy a fully self-hosted RustDesk server with Docker Compose, HTTPS via Caddy reverse proxy, and secure relays for remote desktop access outside your local network.
Deploying ChatterUI with Docker Compose
Self-host the ChatterUI web application on Linux using Docker Compose. This guide covers installation, reverse proxy configuration, troubleshooting, and maintenance.
Vaultwarden vs Bitwarden: The Definitive Self-Hosted Password Manager Guide (2026)
A rigorous technical comparison between Vaultwarden and official Bitwarden. Complete deployment guide with WebSocket support, Tailscale zero-trust, and encrypted backups.
Latest Technical Guides & Runbooks
Practical tutorials and deployment runbooks.
Run Llama 3 Locally with Ollama: A Step-by-Step Self-Hosted AI Guide
Learn to install and run Llama 3 locally using Ollama v0.33.2 with Docker Compose, including security hardening, reverse proxy setup, and troubleshooting.
Chroma DB vs. pgvector: Latency Benchmarks, Memory Footprint & Migration Runbook
Compare Chroma DB and pgvector for production homelab RAG pipelines. A step-by-step architecture, deployment, backup, and zero-trust access guide for 2026.
LocalAI vs Ollama in 2026: The Definitive Self-Hosted AI Showdown
Deep technical comparison between LocalAI v4.9.0 and Ollama v0.33.2 for homelab users — architecture, performance, GPU support, and deployment patterns.
Perplexica v0.3.6 Architecture: Self-Hosted Deep Search with Local LLMs & SearXNG
Deploy Perplexica MCP v0.3.6 in your homelab with Docker Compose, Caddy reverse proxy, Tailscale zero-trust access, automated backups, and expert troubleshooting.
Open WebUI + Ollama: Complete Self-Hosted AI Setup Guide (2026)
Step-by-step Docker Compose guide to deploy Open WebUI v0.11.2 with Ollama v0.33.2. Includes requirements, config, reverse proxy, backups, and troubleshooting.
TorchRuntime API in Production: High-Throughput Model Serving & CUDA Optimization
Step-by-step guide to self-host Torchruntime API examples in 2026: from bare metal prep to zero-trust Tailscale access, automated backups, and troubleshooting.
Ollama & Open WebUI: Complete Self-Hosted AI Stack Guide (2026)
Deploy a private, self-hosted ChatGPT alternative with Ollama and Open WebUI in Docker. Step-by-step GPU acceleration, security, and automated backups.
Weaviate on Low-Power ARM64 Nodes: Memory Optimization & Persistent NVMe Search
Step-by-step production deployment of Weaviate vector database on Raspberry Pi (ARM64). Covers Docker Compose, reverse proxy, Tailscale, automated backups, and troubleshooting.
Self-Hosted AI on Homelab Hardware: A Realistic 2026 Guide to Requirements, Sizing, and Deployment
Stop guessing: learn the true CPU, RAM, and GPU needs for running LLMs, Stable Diffusion, and Whisper on your own hardware. A practical guide with Docker Compose examples and sizing tables.
Why Self-Hosted?
No data leaves your server. Zero telemetry or third-party cookies.
Local GPU & CPU inference, zero cloud latency, operates completely offline.
One-time setup on your hardware, lifetime ownership with full autonomy.