The AI stack on Android.

There are two paths here. The easy path is the official chat apps — enough for most people. The power path is Termux, a real Linux terminal that runs on Android, where the command-line tools live.

Why this first: pick your path. The apps give you AI in your pocket today; Termux is the foundation for the optional power tools in Steps 2–4.

From the Google Play Store, install the official apps: Claude, ChatGPT, and Google Gemini. Sign in with your accounts and you have chat anywhere you go. If you never touch a terminal, that's perfectly fine.

Termux turns your phone into a tiny Linux machine with a real command line.

Open Termux, then update it and install the basics:

pkg update && pkg upgrade
pkg install nodejs git

Anthropic's AI coding agent — the same kind of assistant that built this page. It lives in the terminal, reads and edits real files, and runs commands for you.

Why you want it: it does actual multi-step work, not just chat. On a phone this is the advanced Termux route.

npm install -g @anthropic-ai/claude-code

claude

The first run signs you in to your Anthropic account. After that, just type what you want in plain English.

OpenAI's command-line coding agent. Same idea as Claude Code, different brain — handy as a second opinion or when you've used up one tool's quota.

Why you want it: variety. Different models are stronger at different things; having both means you're never stuck.

npm install -g @openai/codex

codex

First run lets you sign in with your ChatGPT/OpenAI account. Then describe what you want, same as Claude.

Google's command-line AI agent. Notable for a very generous free tier and an enormous memory (context window) for long documents.

Why you want it: free headroom. Great for big, sprawling tasks before you spend on the others.

npm install -g @google/gemini-cli

gemini

First run signs you in with a Google account. The free tier is large — you likely won't pay anything to start.

A coding agent from Nous Research — "the agent that grows with you." Same idea as Claude Code, Codex, and Gemini, with two twists: it's self-improving (it learns your preferences over time), and it's model-agnostic — you point it at whichever brain you want (Nous, OpenAI, Anthropic, OpenRouter, and more).

Why you'd add it: it's the most model-flexible of the bunch — handy for staying un-locked-in (see the future-proofing principles).

pkg install python
pip install hermes-agent
hermes postinstall

hermes setup
hermes --tui

During setup it asks how you want to sign in — an API key, or an OAuth login via hermes setup --portal. It works with the Nous Portal, OpenAI, Anthropic, OpenRouter, and others.

A private network (a "mesh VPN") that connects all your devices to each other securely — your PCs, your Macs, this phone, your NAS — as if they were in the same room, from anywhere in the world.

Why you want it: on a phone this is the big one. Once connected, the phone becomes a remote control into the real computers where the heavy tools live.

Install the official Tailscale app from the Google Play Store. Open it and sign in with the same account as your other devices, so they all join one private network.

Runs AI models on your own hardware instead of the cloud — free, private, offline. On a phone, the trick is to use a model that's hosted elsewhere, not to host it on the phone.

Why you want it: no per-use cost and nothing leaves your network — and a phone makes a great front-end to a model running on a beefier machine.

curl http://YOUR-MACHINE-TAILSCALE-NAME:11434/api/generate -d '{"model":"llama3.2","prompt":"hello"}'