Why? Multi-tenant environments. First, we need to understand a few differences between environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

So

• When you run Claude Code on your local MacBook, the first two are always local. The third is usually the Claude.ai server.
• When you ssh to a virtual private server (VPS) and install Claude Code there, the first two are your remote server. The third is still the Claude.ai server.
• When you run Claude RC on your virtual private server and code from your iPad using the Claude app, the end-user UI is on your iPad, the agent runtime environment is on your VPS, and the server is still Claude.ai.

Most people physically separate their tenancy, such as Claude Code, from their personal vs. work laptops. So in most cases, it's not a big deal.

But when you need multi-tenancy, it becomes super stressful. For example, say you have two different toolkits:

• personal toolkits (personal Notion, personal Sentry, personal Linear)
• workplace toolkits (company Notion, company Sentry, company Linear)

Most MCP auth states or code harnesses don't support profiles, so you can only log in to one.

So therefore... a natural evolution was to have both:

• a personal VPS with all personal toolkits set up
• a workplace VPS with all workspace toolkits set up

to physically isolate tenancies.

Now we've solved the multiple-profile issue, but the client's problems persist. Now let's get back to the environments:

• End-user UI
• Agent Runtime Environment
• LLM Server

All MCP auth or toolkit auth info should always be saved in the Agent Runtime Environment IMHO. However, a surprising number of harnesses tie them to the LLM server (such as Codex Apps or Claude.ai Plugins) or put them in the end-user UI (Claude Desktop or Codex Desktop).

Now the problem is:

• If the auth data is put on the LLM server, you cannot reuse LLM accounts across tenants
• If the auth data is put on the end-user UI, you cannot use the same app to access multi-tenants.

The only way to reliably isolate different auth information is thus:

• You ssh to a virtual private server (VPS) and run Claude Code there. Never use LLM server plugins.

Then

• End-user UI
• Agent Runtime Environment

are both isolated VPS, and

• LLM Server holds no information on the tenancy

This way, you can provide different toolkits, creating multiple dev environments.

컴퓨트로늄 컴퓨트로늄

Yarn is another package manager for JavaScript that Facebook developed as a more efficient and reliable alternative to npm. It was released in 2016, several years after npm.

Here are a few features of Yarn:

1. Speed and Efficiency. Yarn is known for its speed and efficiency. It uses a deterministic installation algorithm that ensures the exact dependencies are installed in the same structure every time.
2. Offline Mode. Yarn has a feature where it can install packages from a local cache if they have been downloaded before, making it possible to work offline.
3. Security. When installing packages, Yarn first suggestions their checksums for integrity before actual code execution takes place.
4. Workspaces. Yarn has a native feature called "workspaces" to manage mono repo (mono repository) architectures, which can make it easier to manage projects with multiple sub-packages more accessible.
5. Compatibility. Yarn supports the npm registry, so you can access the many libraries that npm hosts.

Comparison between npm and Yarn

• Performance. When Yarn was first released, one of its main advantages over npm was its performance. Yarn offered faster package installation. However, since npm version 5, the performance gap has significantly reduced.
• Security. Yarn has the edge over npm because it uses checksums for every package before they are installed, ensuring its integrity.
• Offline mode. Yarn can reuse previously downloaded, making it possible to install packages without an internet connection, which npm can't do.
• Workspaces. While both package managers support managing multiple packages within the same top-level root package, Yarn's workspace feature is more advanced and configurable.
• Lockfile. Both npm and Yarn generate a lock file (package-lock.json for npm, yarn. lock for Yarn), which helps lock dependencies down to a specific version, making installations more reliable between different systems.
• Documentation. npm tends to have better and more comprehensive documentation than Yarn.