AI Coding Workstation (Claude Code, Codex, Gemini CLI)

Deploys a cloud development box with VS Code in the browser (code-server), a terminal and optional SSH. Claude Code, OpenAI Codex CLI, Gemini CLI and OpenCode come preinstalled at pinned versions, with your home directory on a volume. You bring your own subscriptions or API keys.

What you get

  • One service built on the code-server image (Ubuntu 24.04 LTS) with a browser IDE protected by a generated PASSWORD
  • Claude Code, Codex CLI, Gemini CLI and OpenCode, each installed from its vendor's npm package at a pinned version
  • Node.js, Python, uv, git, gh and build tools
  • A Railway volume at /home holding projects, CLI logins and VS Code settings
  • Optional SSH through a Railway TCP proxy, using SSH_PASSWORD or SSH_AUTHORIZED_KEYS

Good for

  • Run AI coding agents on long refactors inside tmux and keep them going while you are offline
  • A consistent dev environment you can open from any device, including tablets and locked-down laptops
  • Remote pair programming or demos without sharing your own machine
  • Trying several AI coding agents on the same repository

Services in this template

  • Workstation · from baranberkay96/ai-coding-workstation-railway

Questions people ask

How do I log in?

Open the service URL and enter the PASSWORD value from the service's Variables tab. Then sign in to the tools you use: claude, codex login --device-auth, NO_BROWSER=true gemini, opencode auth login, or set ANTHROPIC_API_KEY, OPENAI_API_KEY or GEMINI_API_KEY as variables. For SSH, copy the TCP proxy host and port from Settings, Networking.

What persists across redeploys?

Everything under /home/coder: projects in ~/workspace, CLI logins, VS Code extensions and settings, and per-user npm and pip installs. System packages installed with sudo apt reset on redeploy.

How do I upgrade the tools?

code-server, Node.js and each CLI version are build arguments at the top of the Dockerfile; change them and redeploy. For a newer CLI without a rebuild, run npm i -g {package}@latest as coder; it installs into ~/.npm-global on the volume.

What does it cost to run?

You pay Railway for the CPU and memory the box uses; the sources give no measured figure. Usage of the AI tools is billed separately by their vendors. It is a single-user machine with one replica, so deploy one per person for a team.

Are there licence limits?

Claude Code is proprietary and its use is subject to Anthropic's terms. Codex CLI and Gemini CLI are Apache-2.0, OpenCode and code-server are MIT. This is a community template, not affiliated with the tool vendors.

Full template README

Deploy and Host AI Coding Workstation with Railway

A cloud development box with VS Code in the browser (code-server), a full terminal and optional SSH. Claude Code, OpenAI Codex CLI, Gemini CLI and OpenCode come preinstalled, along with Node.js, Python, uv, git, gh and build tools. Your home directory, projects and CLI logins live on a persistent volume.

About Hosting AI Coding Workstation

AI coding agents work best on a machine that stays online: long tasks keep running after you close your laptop, and you can check in from any browser or phone. Hosting one yourself means maintaining a Linux box with an IDE, the agent CLIs, language runtimes, secure remote access and storage that survives rebuilds. This template builds on the official code-server image (Ubuntu 24.04 LTS), installs each AI CLI from its vendor's official npm package at a pinned version, mounts a Railway volume at /home, protects the IDE with a generated password and offers SSH through a Railway TCP proxy. You bring your own subscriptions or API keys.

Common Use Cases

  • Run Claude Code, Codex, Gemini CLI or OpenCode on long refactors and keep them going in tmux while you are offline
  • A consistent dev environment you can open from any device, including tablets and locked-down work laptops
  • Remote pair programming or demos without sharing your local machine
  • Trying several AI coding agents side by side on the same repository

Dependencies for AI Coding Workstation Hosting

  • A Railway volume for /home (included)
  • Optional: accounts or API keys for the AI tools you use (Claude Pro/Max or Anthropic API, ChatGPT or OpenAI API, Google account or Gemini API key, any OpenCode provider)
  • Optional: a GitHub token for private repositories

Deployment Dependencies

Implementation Details

Service Source Purpose
Workstation Dockerfile based on codercom/code-server:4.141.0-noble Browser IDE on port 8080, optional sshd on 2222 (TCP proxy), AI CLIs, volume at /home

First login

  1. Open the service URL and enter the value of PASSWORD from the service's Variables tab.
  2. Open a terminal and start a persistent session: tmux new -A -s main.
  3. Sign in to your tools: claude, codex login --device-auth, NO_BROWSER=true gemini, opencode auth login, or set ANTHROPIC_API_KEY, OPENAI_API_KEY, GEMINI_API_KEY as variables.
  4. For SSH, copy the TCP proxy host and port from Settings → Networking and run ssh -p {port} coder@{host} with SSH_PASSWORD. For key-only access, put your public key in SSH_AUTHORIZED_KEYS and clear SSH_PASSWORD.

What persists: everything under /home/coder (projects in ~/workspace, CLI logins, VS Code extensions and settings, per-user npm and pip installs). System packages installed with sudo apt reset on redeploy.

Scaling: this is a single-user machine, so keep one replica. Railway scales the service's RAM and CPU vertically up to your plan limit, which covers parallel agents and builds. For a team, deploy one workstation per person.

Pinning and upgrades: code-server, Node.js and each CLI version are build arguments at the top of the Dockerfile. Change them and redeploy. To get a newer CLI immediately without a rebuild, run npm i -g {package}@latest as coder; it installs into ~/.npm-global on the volume, which comes first in PATH.

Why Deploy AI Coding Workstation on Railway?

Railway gives the workstation a stable HTTPS URL, a TCP proxy for SSH and a persistent volume with no server administration. It keeps your agents running while you are away, and you pay for the CPU and memory the box actually uses.

Guides for this template

View AI Coding Workstation (Claude Code, Codex, Gemini CLI) on railway.com

Similar templates

TemplateCategoryDeploymentsDeploys
Chatwoot
A customer communication platform
Other5,871
Ubuntu-Linux
Ubuntu terminal accessible via web browser
Other4,926
Ubuntu SSH + Claude
ARA TM —SSH server with root access + Claude Code pre-installed.
Other4,682
Debian-Linux
Debian terminal accessible via web browser.
Other2,883
Code Server
VS Code in the browser
Other2,787
Kali Linux (Web Terminal)
Instant Kali Linux browser terminal powered by ttyd
Other2,632