<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Self-Hosting on Hitesh Pattanayak</title><link>/tags/self-hosting/</link><description>Recent content in Self-Hosting on Hitesh Pattanayak</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Sat, 25 Jul 2026 12:00:00 -0700</lastBuildDate><atom:link href="/tags/self-hosting/index.xml" rel="self" type="application/rss+xml"/><item><title>GitOps Homelab: Adding LiteLLM as a Unified AI Gateway for Ollama and Cloud Models</title><link>/posts/gitops-homelab-adding-litellm-as-a-unified-ai-gateway-for-ollama-and-cloud-models/</link><pubDate>Sat, 25 Jul 2026 12:00:00 -0700</pubDate><guid>/posts/gitops-homelab-adding-litellm-as-a-unified-ai-gateway-for-ollama-and-cloud-models/</guid><description>How to add LiteLLM as a proxy layer on top of Ollama and Open WebUI, unifying local and cloud AI models behind a single OpenAI-compatible endpoint, managed via GitOps with ArgoCD.</description></item><item><title>GitOps Homelab: AI-Powered CLI Coding with Aider, LiteLLM, and Local Models</title><link>/posts/gitops-homelab-ai-powered-cli-coding-with-aider-litellm-and-local-models/</link><pubDate>Sat, 25 Jul 2026 12:00:00 -0700</pubDate><guid>/posts/gitops-homelab-ai-powered-cli-coding-with-aider-litellm-and-local-models/</guid><description>How to wire the LiteLLM gateway into aider for terminal-based AI pair programming, using model aliases, a port-forward systemd service to work around SSL issues, and the current 3B model lineup running on a GTX 1650.</description></item><item><title>GitOps Homelab: Running Ollama and Open WebUI on K3s with ArgoCD</title><link>/posts/gitops-homelab-ollama-and-open-webui-on-k3s-with-argocd/</link><pubDate>Tue, 21 Jul 2026 14:00:00 -0700</pubDate><guid>/posts/gitops-homelab-ollama-and-open-webui-on-k3s-with-argocd/</guid><description>The second part of the GPU homelab series: bootstrapping a full GitOps platform on k3s using ArgoCD&amp;rsquo;s app-of-apps pattern, wiring up Ollama and Open WebUI, and the four gotchas that will trip you up.</description></item><item><title>GPU-Enabled Kubernetes Homelab: Setting Up a GTX 1650 Laptop as a k3s Node</title><link>/posts/gpu-enabled-kubernetes-homelab-setting-up-a-gtx-1650-laptop-as-a-k3s-node/</link><pubDate>Tue, 21 Jul 2026 12:00:00 -0700</pubDate><guid>/posts/gpu-enabled-kubernetes-homelab-setting-up-a-gtx-1650-laptop-as-a-k3s-node/</guid><description>A step-by-step walkthrough of turning an old GTX 1650 laptop into a GPU-enabled single-node k3s cluster, explaining the why behind each layer of the stack and the two non-obvious gotchas that will trip you up.</description></item></channel></rss>