Auggie, on your phone and your desktop

Auggie is the agent whose two names catch people out. The CLI is Auggie; the vendor is Augment Code; the Happier documentation page is filed at /providers/augment and is the same page. Underneath the naming it is an npm install of @augmentcode/auggie, run under whichever Augment entitlement that computer is signed in with. Augment Code’s own framing is that it puts agentic coding “in your terminal, on your server, or anywhere your code runs”, which is the half of the product Happier is here for.

Indexing is the setting to know about. Auggie can index a repository, and Happier does not turn that on for you: the flag is added only when HAPPIER_AUGGIE_ALLOW_INDEXING is set in the environment of the session, so a repository you have not decided about is one it has not indexed. It is opt-in per environment rather than a global preference, which is the right shape for the case where one of your computers holds work code and another does not.

Permissions are the other thing this integration does its own way, because Auggie wants them tool by tool. Happier expands a single choice into a --permission rule for every tool the CLI publishes — its editing and file tools, its process tools, web search and fetch, its task list, and its named sub-agents for reviewing code, building components, designing databases and writing tests. Read-only adds Auggie’s own ask mode and then denies the editing and process tools by name on top of it, rather than trusting one flag to cover both. Tools going the other way arrive through the happier tools shell bridge, since Auggie takes no MCP inventory directly.

Auggie is Augment Code’s command-line agent. happier auggie runs it against your repository from an npm-installed binary, with the account the CLI is already signed in with.

What you get for putting Happier in front of it is portability and one place for the interruptions: the transcript on a phone, the diff on a tablet, and the permission requests from every agent you run collected in a single inbox instead of scattered across terminal windows.

The iOS and Android apps, the desktop app for macOS, Windows and Linux, and app.happier.dev are all clients onto the Auggie process running on your computer — not read-only mirrors. Answer a permission request, send the next instruction, browse the repository, read the diff. The transcript is end-to-end encrypted before it leaves your computer, so the server carrying it holds ciphertext.

Happier installs on the computer that already holds your repository, and happier auggie starts Auggie there as an ordinary subprocess, in the directory you point it at, signed in the way you signed it in. There is no gateway between the agent and Augment Code, and no copy of your source anywhere else.

Happier looks for auggie on your PATH first and runs the copy you installed. If there is not one, it can install @augmentcode/auggie into ~/.happier/tools/providers/auggie/ — its own directory, not your global npm prefix. A copy you manage yourself is never replaced or upgraded behind your back.

Augment Code’s own install and sign-in guide is at docs.augmentcode.com/cli/setup-auggie/install-auggie-cli. Happier does not mirror it, because a copy of someone else’s install instructions is a copy that goes stale.

Configuration reference for the Happier side — Auggie in the Happier docs.

Auggie is one of 13 command-line coding agents Happier runs, and they share one session list, one permission inbox, one set of keyboard shortcuts and one MCP configuration.

You define an MCP server once, and because Auggie does not consume MCP directly, Happier hands the same tool surface to it through the happier tools shell bridge instead — the same tools, delivered as commands it can run. The app previews the effective tool surface before a session starts, so which one you got is visible rather than inferred.

That matters most on the days you are running more than one: sessions from different vendors side by side, and a notification tap opening the session that raised the request rather than the app’s front door. The full list is here.

Typing happier auggie in a terminal starts the session right where you are standing, and the same session is in the app at the same time. What you read in that shell is Happier’s own display of the session — the transcript, the permission prompts, the tool output — rather than Auggie’s interface. Nobody has to give up the terminal to get a phone client.

There is no hand-off to Auggie’s own TUI. That exists for Claude Code, Codex and OpenCode, and for Auggie the session stays Happier’s on both ends. happier attach <session-id> lists the sessions on that computer and marks the ones it cannot reattach, rather than failing after you pick one.

The attach guide lists the cases instead of promising all of them.

One command on the computer that holds your code, then happier auggie in the repository you want to work in.

Walkthroughs are in the guides. All of it is MIT-licensed, and the relay is one you can run yourself.