Open-source app for Qwen Code

Qwen Code calls itself “the open-source AI coding agent that lives in your terminal”, and its own repository is candid about where it came from: it started as a fork of Google’s Gemini CLI at v0.8.2 and has developed separately since. Knowing that saves you a guess later: a lot of what the CLI does will look familiar if you have used the other one, and the flags are the place it shows.

Qwen carries a single approval mode of its own, and Happier translates into it at launch rather than layering a policy of its own on top. The command is qwen --acp --approval-mode, and the value is plan when you chose Read-only or a plan mode, auto-edit for Safe YOLO, yolo when you have decided you do not want to be asked, and default the rest of the time. Change the setting in the app and that flag is what changes, so what the CLI enforces and what the app shows you cannot drift apart.

Sign-in is the same shape: Qwen keeps its authentication behind a slash command, so the provider page starts qwen on the computer you picked and types /auth into it for you. What Happier will not do is go rummaging afterwards to work out whether it took — some of these commands print credentials to a terminal, so the status probe is left off and the page says Unknown rather than reading something it should not. Tools reach it through the happier tools shell bridge instead of native MCP: the same surface, handed over as commands it can run.

Qwen Code is Alibaba’s terminal coding agent, distributed as an npm package. happier qwen starts it in your repository with the credentials the CLI already has, and does not put a model of its own in the path.

If you are on Qwen because of where your models are hosted rather than because of an editor preference, the useful part here is that nothing about that changes. The agent runs where your code is; Happier only makes the conversation portable.

The iOS and Android apps, the desktop app for macOS, Windows and Linux, and app.happier.dev are all clients onto the Qwen Code 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 qwen starts Qwen Code 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 Alibaba, and no copy of your source anywhere else.

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

Alibaba’s own install and sign-in guide is at qwenlm.github.io/qwen-code-docs/. 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 — Qwen Code in the Happier docs.

Qwen Code 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 Qwen Code 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 qwen 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 Qwen Code’s interface. Nobody has to give up the terminal to get a phone client.

There is no hand-off to Qwen Code’s own TUI. That exists for Claude Code, Codex and OpenCode, and for Qwen Code 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 qwen 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.