AutoBuilder

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.

191109

The only thing I missed about my Windows computer was locking the screen since I was so used to locking my computer with ⊞Win+L. Mac offered an alternative called the Hot Corner. But it never was so intuitive and fast as pressing ⊞Win+L. However, Mac now supports locking the computer by pressing ⌘Command+L from macOS Mojave.

How do I do it?

1. Go to System Preferences.

2. Go to Keyboard → Shortcuts → App Shortcuts and press + at the bottom.

3. On your Menu Bar, press the  Apple Logo. Check the name of ^Control+⌘Command+Q. It is responsible for locking your Mac. Remember the name of the menu.

4. Go back to the Preference app. Select All Applications at Application Setting. Next, enter the Menu Title you have just checked. This title will vary according to your macOS Language Preference. Finally, enter ⌘Command+L at Keyboard Shortcut. You can enter it here if you want to lock your Mac with Keyboard Shortcut other than ⌘Command+L. Press Add if you are finished.

5. Now you can see that the same Lock Screen option at your menu bar will show the Keyboard Shortcut you just changed.

This method works in almost every case. Sometimes, the app will have ⌘Command+L as its Keyboard Shortcut. One example is the System Preferences app that uses the ⌘Command+L as going to the Lobby of System Preferences. I have never seen any other cases where ⌘Command+L doesn't work as expected.

• If some app uses ⌘Command+L as their default shortcuts, you can set them to some other random shortcuts, clearing the path for the Lock Screen shortcut.

• You can now click the Touch ID button from macOS Big Sur to lock your Mac.