• AutoBuilder

Cursor is incredibly good harness.

Opus is also not Oputhetic anymore

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.

Multiple issues are combined.

Docusaurus 2.3.0 useSyncExternalStore Bug

Using Tabs will break with React 18 and Docusaurus v2.3 · Issue #8592 · facebook/docusaurus

Vercel and Cloudflare Build Errors

On Cloudflare's side:

16:49:17.136    ✔ Server: Compiled successfully in 3.74m16:50:22.579    Segmentation fault16:50:22.595    Failed: build command exited with code: 13916:50:23.859    Failed: an internal error occurred

On Vercel's Side:

[success] [webpackbar] Server: Compiled successfully in 3.49mError: Command "yarn run build" exited with 129

Why..? I changed no config

230129

Investigating RAM Options. Supported a ticket to Cloudflare

--max-old-space-size=4096

Did not help.

OH FIGURED IT OUT. It was because of insufficient RAM. When Docusaurus seals the assets (at the end of the build cycle), the RAM usage spikes to ~4.5 GB.

Configuring Cloudflare Pages and Vercel with the following argument fixed the problem!

--max-old-space-size=8192

-- Nope. Did not solve the problem.

So I ended up using Cloudflare Wrangler to build on my device and then sending the build result to Cloudflare. Anyways, the issue seems to be resolved.