• Debian Setup
• 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.

181028

• Node.js 앱을 AWS EB에서 Heroku로 옮기기

I have used AWS Elastic Beanstalk for a while and figured Heroku has several advantages over AWS. So I have migrated my AWS EB app called KMLA Forms to Heroku. For your information, KMLA Forms is a web app that simplifies writing necessary official documents in my school, KMLA.

Few advantages I found:

1. Money. AWS costs money after its free tier limit. Since some of the students in my school used my web app, I have got some traffic, and AWS started to ask me about ~$10/month. As far as I know, there is no free tier traffic limit on Heroku.
2. Native HTTPS support. Heroku natively supports HTTPS since every dyno app can use Heroku's domain. AWS EB, on the other hand, does not provide this. You need to configure your web domain and HTTPS Certificate for each web domain. Not valid for casual developers.

I had to make only minimal changes to app.js and package.json.

AWS Version

// ...
http.createServer(app).listen(8081, '0.0.0.0')
console.log('Server up and running at http://0.0.0.0:8081')

Heroku Version

// ...
const port = process.env.PORT || 8000
// ...
app.listen(port, () => {  console.log('App is running on port ' + port)})

Also, I have added "start": "node app.js" in package.json. Codes are on GitHub, and the web is launched here.