Choosing Your Cloud Sandbox

Can’t install software? Don’t want to learn terminal commands yet? You can still build real things with AI tools — here’s how to choose.

Why this lesson exists

The rest of this course teaches CLI tools that run in a terminal. But not everyone can install software on their machine — locked-down work computers, Chromebooks, school labs, and mobile devices all make local installation difficult or impossible.

The good news: as of 2026, every major AI CLI tool now has a first-party cloud sandbox. This lesson helps you choose the right one. The next lesson walks you through setup.

The cloud sandbox landscape

Claude Code Web

What it is: Anthropic’s Claude Code, running in your browser at claude.ai/code. It connects to your GitHub repositories and can clone, edit, test, and commit code — all without a terminal.

Best for: Full project editing via GitHub. The closest browser equivalent to the terminal CLI experience.

Limitations: Only works with GitHub repos (no local files), requires a subscription, no offline access. See M4L5 cheat sheet for current pricing.

Codex Cloud

What it is: OpenAI’s Codex agent running at chatgpt.com/codex. It plans, executes, and iterates on coding tasks autonomously in a sandboxed environment.

Best for: Autonomous task execution. Describe what you want and let it build.

Limitations: Each task runs in a fresh environment (no persistent state between tasks), requires a subscription. See M4L5 cheat sheet for current pricing.

GitHub Codespaces

What it is: A full Linux development environment running in your browser. You get VS Code, a terminal, file access, and the ability to install any tool — including Claude Code, Gemini CLI, Codex CLI, and Copilot CLI.

Best for: The most flexible option. Everything a local terminal can do, in the browser.

Limitations: Free tier has limited hours, sessions time out after inactivity, codespaces auto-delete after extended inactivity. See M4L5 cheat sheet for current limits.

Google Cloud Shell

What it is: A free browser-based Linux terminal at shell.cloud.google.com. Pre-installed with common dev tools. Best for practicing terminal commands.

Best for: The fastest zero-setup terminal. Great for Module 3 command practice.

Limitations: Idle timeout, weekly hour limit, limited for full project development. Install Node via nvm (lives in ~/) so CLI tools persist. See M4L5 cheat sheet for current limits and Module 3, Lesson 5 for more details.

ChatGPT Interpreter

What it is: ChatGPT with code execution enabled. Runs Python code, processes uploaded files, generates downloadable results — all inside a browser conversation.

Best for: Single-file tasks, data analysis, file conversion, quick scripts.

Limitations: Upload/download only (no persistent file tree), Python-focused, cannot install npm packages or connect to GitHub.

Gemini Web

What it is: Google’s Gemini AI in the browser at gemini.google.com. Generous free tier with conversational AI and some code execution.

Best for: Conversational tasks, brainstorming, planning, research with a generous free tier.

Limitations: Cannot run shell commands, no file tree, no package installation.

Which sandbox fits your situation?

Scenario 1: Locked-down machine (work, school, or government)

You can’t install software, and your IT department controls your environment.

Best option: Codespaces — runs entirely in the browser, gives you a full Linux terminal, and lets you install CLI tools inside the codespace. If GitHub is blocked, try Cloud Shell for terminal practice or Claude Code Web for project editing.

Scenario 2: Personal machine, but you want to avoid setup

You could install tools, but you’d rather start building immediately.

Best option: Claude Code Web — connects to your GitHub repos and gives you the closest experience to terminal CLI tools, with zero setup. When you’re ready for more flexibility, Codespaces lets you install any tool from this course.

Scenario 3: You want full terminal power from the browser

You want the complete CLI experience — multiple tools, shell commands, package installation — without any local setup.

Best option: Codespaces — it is a real Linux machine. Install Claude Code, Gemini CLI, Codex CLI, and Copilot CLI just like you would locally. The free tier is generous enough for learning.

🏛️In Your Field: Government / State Devclick to expand

Data sovereignty warning: All cloud sandboxes process your code on external servers. Do not paste sensitive, PII, CUI, or classified data into public sandboxes without authorization from your security office. Government machines often block software installs and may restrict certain web services. Check whether your agency allows access to claude.ai, github.com, or chatgpt.com. If GitHub is accessible, Codespaces may be your best path — it runs entirely in the browser and does not require local installation. Talk to your IT team about approved cloud development environments.

📊In Your Field: MIS / Businessclick to expand

Many university computer labs restrict software installation. Codespaces is ideal for class projects — every student gets the same environment, no setup conflicts, and the free tier is usually sufficient for coursework. Your professor may also have a GitHub Classroom setup that provisions Codespaces automatically.

🧬In Your Field: Biotechclick to expand

If your lab uses shared workstations where you cannot install software, Codespaces gives you a clean environment for bioinformatics scripting. For quick data processing tasks (parsing CSVs, reformatting FASTA files), ChatGPT Interpreter works well — upload the file, describe the transformation, download the result.

Honest tradeoffs

What you gain with cloud sandboxes:

• Zero setup time — start building immediately
• Works on any device with a modern browser
• No risk of breaking your local environment
• Easy to share your environment with collaborators (Codespaces)

What you lose:

• Local file access (your files live in the cloud, not on your machine)
• Offline capability
• Full control over your development environment
• Some automation features that depend on local shell access

For most tasks in this course, cloud sandboxes work well. The terminal path becomes important when you need offline access, deep local integration, or maximum performance.

🔍Devcontainer templates: pre-configured sandboxes

If you’re using Codespaces, devcontainer templates can pre-configure your entire environment — tools, extensions, settings — in one click. Templates like wandb/vibes and community-maintained configurations set up multiple AI CLI tools automatically. This is an advanced option; the basic Codespaces setup from this lesson is all you need to get started. Explore devcontainer templates later when you want a reproducible, shareable environment.

When you’re ready for more

Terminal skills unlock more flexibility — local file access, offline work, custom automation, and the full power of every CLI tool. If you started here because you could not install software, that is completely fine. When your situation changes, Module 3: Command Line Basics is ready for you.

The orchestration skills you learn in this course — planning, prompting, reviewing, iterating — transfer to any tool, browser-based or terminal-based. Start where you can, grow when you are ready.

Key takeaways

• Six cloud sandbox options exist — each with different strengths, from full project editing to quick data processing
• Claude Code Web is the closest browser equivalent to the terminal CLI experience — it connects to your GitHub repos and edits code directly
• Codespaces is the most flexible — it is a real Linux machine where you can install any CLI tool from this course
• Cloud Shell is the fastest zero-setup terminal — great for practicing commands
• The terminal path is still the most powerful. When you can install software, Module 6 unlocks the full experience
• Your orchestration skills transfer. Good prompts, clear planning, and thoughtful review work the same way in any tool

Ready to set up your sandbox? Continue to the next lesson to get hands-on.