Can Yado be vibe coded?
Run Claude Code from your phone, on a container that is not your laptop
Claude Code was never built to leave the laptop. A chat interface is easy. A terminal into a remote container, also fine. The pain starts when you want Claude, the container, and the app to forget they're three completely distinct entities and behave as one thing: signing in with one tap, when on paper that can only happen in a terminal. A chat, when underneath it is always a terminal. Infra that's fast and that keeps one person's AI away from everyone else's code. I thought that was weeks of work. It was months.
Jump to the build brief ↓Checked Jul 2026
What you pay today, before any DIY hosting
high editorial confidence
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends.
- Build the focused developer workflow you use repeatedly, with local configuration.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- a real chat with your Claude account instead of a terminal driven by a phone keyboard
- a machine that sleeps at zero and wakes before you type instead of a box you pay for all week
- one tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once
- diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building
- Reliability at the vendor's scale is an operations problem, not a prompt.
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
Why people still pay
Because the contained build is a pet. You keep the box alive, you keep the proxy alive, you patch it every time Claude Code shifts under you, and you pay for a machine that idles all week. Some people like pets, and if that's you, keep it. Yado is the version where none of that is yours. It wakes when you open the app and costs nothing the rest of the time, signing in is one tap instead of an SSH session, and when Claude Code moves, that's my problem now. You still bring your own Claude account. You're paying me for the boring half.
Reliability at the vendor's scale is an operations problem, not a prompt.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to Yado
Context
**Yado** — Run Claude Code from your phone, on a container that is not your laptop. It currently costs $9.99/mo.
Claude Code was never built to leave the laptop. A chat interface is easy. A terminal into a remote container, also fine. The pain starts when you want Claude, the container, and the app to forget they're three completely distinct entities and behave as one thing: signing in with one tap, when on paper that can only happen in a terminal. A chat, when underneath it is always a terminal. Infra that's fast and that keeps one person's AI away from everyone else's code. I thought that was weeks of work. It was months.
This brief describes a focused, single-operator replacement for the part of Yado that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends.
Build the focused developer workflow you use repeatedly, with local configuration.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
An always-on Linux box or a $5 VPS.
A Claude Pro or Max subscription.
A domain for HTTPS, or Tailscale.
A laptop, once, to do the Claude login over SSH.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build me a phone-reachable Claude Code setup to replace Yado. Requirements:
Runs on one always-on Ubuntu box I already own, a $5 VPS is fine. I reach it
from Safari on my phone, there is nothing to install on the phone.
Install Claude Code on the box and log it in by hand once over SSH, so the
credentials sit on disk and nothing has to handle auth later. This step needs
a laptop, say so in the README.
Serve the terminal with ttyd running `tmux new -A -s claude`, so the session
survives a dropped connection and keeps working while my phone is locked.
Put Caddy in front for automatic HTTPS on a subdomain, with basic auth
credentials read from .env. If I already run Tailscale, bind ttyd to the
tailnet address instead and skip Caddy. No accounts, no telemetry, everything
stays on my box.
Make it usable with a thumb: start ttyd with `-t fontSize=18`, and write a
~/.tmux.conf with mouse mode on so I can scroll and switch panes by tapping.
Add a Claude Code Stop hook in ~/.claude/settings.json that curls a private
ntfy.sh topic, so my phone buzzes when a turn finishes instead of me sitting
there watching output.
A `work <repo>` shell function that attaches to the tmux session, cds into
~/code/<repo> and starts claude there. Repos live in ~/code, there is no
database and nothing to migrate.
Out of scope: multiple users and isolation between projects. Do not build a
chat UI over `claude -p`, that is a far bigger project than this one.
README: the one time SSH login, the DNS record for the subdomain, the ntfy
topic name, and an honest warning that if the box goes down there is no way
back in from the phone.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
A real chat with your Claude account instead of a terminal driven by a phone keyboard.
A machine that sleeps at zero and wakes before you type instead of a box you pay for all week.
One tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once.
Diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building.
Reliability at the vendor's scale is an operations problem, not a prompt.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
What you still own after launch
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[Happy](https://github.com/slopus/happy) — MIT mobile and web client for Claude Code, self-hostable, but it remote-controls Claude running on a computer you keep on
[Moshi](https://getmoshi.app/docs/introduction) — a polished mobile terminal that drives Claude Code over SSH, freemium rather than open source, and the machine it connects to has to be yours and switched on
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/yado
You still own the product
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Open-source prior art
MIT mobile and web client for Claude Code, self-hostable, but it remote-controls Claude running on a computer you keep on
View project ↗Moshia polished mobile terminal that drives Claude Code over SSH, freemium rather than open source, and the machine it connects to has to be yours and switched on
View project ↗Before you start
Can Yado be vibe coded?
Partly, if you narrow it. Claude Code was never built to leave the laptop. A chat interface is easy. A terminal into a remote container, also fine. The pain starts when you want Claude, the container, and the app to forget they're three completely distinct entities and behave as one thing: signing in with one tap, when on paper that can only happen in a terminal. A chat, when underneath it is always a terminal. Infra that's fast and that keeps one person's AI away from everyone else's code. I thought that was weeks of work. It was months.
What can an AI coding agent reproduce from Yado?
Serve Claude Code running inside tmux on your own always-on box as a browser terminal, reachable from your phone over HTTPS, with a push when the turn ends. Build the focused developer workflow you use repeatedly, with local configuration. A responsive interface with real empty, loading, success, and error states.
What will a DIY Yado replacement still be missing?
a real chat with your Claude account instead of a terminal driven by a phone keyboard; a machine that sleeps at zero and wakes before you type instead of a box you pay for all week; one tap sign in · the DIY version needs a laptop and an SSH session to log Claude in once; diffs you can read on a small screen · screenshots you can paste in · a live preview of the app you are building; Reliability at the vendor's scale is an operations problem, not a prompt.; The last 20 percent is sync, migration fidelity, speed, and edge cases.
What do I still own after building a Yado alternative?
Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.