Claude Code, Codex, Gemini, Tailscale, Ollama — the five tools every modern AI setup runs on. This site shows you exactly how to install all of them, one device at a time, in plain language with copy-paste commands.
Built for anyone who keeps hearing the names but hasn't had one clean place that walks through the install. Pick your device below and follow the same six steps every time.
Each guide is self-contained — open the one for the machine in front of you and work top to bottom. Got a lot of one kind? You only learn it once, then repeat.
Windows 10 / 11 laptops and desktops. The big one — covers Windows Terminal, winget, and WSL2.
🍎Any Apple Silicon (M-series) or Intel Mac. Homebrew does most of the heavy lifting here.
🐧A DigitalOcean droplet or any Ubuntu/Debian server you reach over SSH. The always-on workhorse.
🤖Run real command-line AI tools on the phone with Termux, or use it as a remote control for your big machines.
📱Apple won't let you install CLIs directly — so this guide turns your phone into a remote into the machines that can.
🧱The hypervisor that runs your VMs and containers. Spin up a dedicated "AI box" that's always available on your network.
🗄️Your file server can quietly host Ollama and Tailscale in Docker, 24/7, with no extra machine running.
☁️Rent power by the hour. Google Cloud's Vertex AI, AWS Bedrock, Azure, and GPU clouds for running big models you can't fit at home.
📋Every install command for every platform on a single printable page. The one to tape next to your desk.
Once you've done it on one device, the rest feel familiar. You're always doing these six things, in this order:
Get a command line open and a way to install software from one (winget, Homebrew, apt). Everything else rides on this.
Anthropic's coding agent — the one you're talking to right now. Lives in your terminal and does real work on your files.
OpenAI's command-line coding agent. A second opinion / second engine that works the same way as Claude Code.
Google's command-line AI. Big free allowance and a huge context window — good as a third tool in the rotation.
A private network that lets all your devices see each other securely, anywhere. The glue that makes 15 machines feel like one.
Runs AI models locally on your own hardware — free, private, offline. Share it across the house over Tailscale.
If the names blur together, read this once. No jargon — just what the tool is, who makes it, and why you'd want it.
| Tool | Who makes it | In one sentence | Why you want it |
|---|---|---|---|
| Claude Code | Anthropic | An AI coding assistant that lives in your terminal and edits real files. | Builds and fixes websites, scripts, and documents by itself. The most capable of the three. |
| Codex | OpenAI | OpenAI's version of the same idea — a command-line coding agent. | A strong second engine; handy when you want a different model's take. |
| Gemini CLI | Google's command-line AI, with a very large free tier. | Generous free usage and a huge memory for long documents. | |
| Tailscale | Tailscale Inc. | A "VPN" that privately connects all your devices to each other. | Reach any machine from any other — phone to PC, laptop to NAS — securely, from anywhere. |
| Ollama | Ollama (open source) | Runs AI models on your own computer instead of the cloud. | Free, private, works offline. No subscription, nothing leaves your house. |
Every AI tool in widespread use — chat assistants, coding agents, AI editors, local models, MCP — organized into four simple layers, with how they interrelate and how to future-proof yourself as new tools (like Anthropic's Mythos) arrive. The one page to read before everything else.