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.

230419

Prehistoric

Where would hn.cho.sh lead us? An AI-powered news portal? Reference: 일일일, News Minimalist. Would it eventually lead to a portal? Or should I remain as a newsletter? Would there be any other form?

After some contemplation...

It should be Super Long Range Radar, The Oracle's Eye, The ALL-SEER that keeps you up to date on specific topics.

AI-powered news portal can never be the answer; it should be a platform where people can proactively seek and search foreign intelligence.

Imagine a workflow...

At Karrot, scraping the news over the internet was a daily activity.

What if we can ask the All-seer to check for keywords 당근 캐롯 and Karrot every day?

An example:

At Simple Analytics, we use AI to detect if new articles on Hacker News or Google Alerts are relevant to our business.

We ask for a rating between 0-100 and why the article is getting that rating.

We send ourselves alerts when rating is 30+

Original Post Link…

Original Post Link

— Adriaan 📊 Simple Analytics (@AdriaanvRossum) March 8, 2023

Themed Newsletters

What if we want to keep ourselves up to date on various topics but in a non-aggressive, Anti-Tiktok manner? Users can ask:

• Hey Heimdall, give me daily reports on Hacker News (the current hn.cho.sh service)
• Hey Heimdall, give me daily reports on TechCrunch
• Hey Heimdall, give me daily reports on 대한민국 연예계 뉴스
• Hey Heimdall, give me daily reports on European Fashion Market

Then Heimdall will give reports every day.