AIToday
Large Language ModelsAI Coding AssistantsZenn AI/MLPublished: Oct 22, 2026, 13:00 JST

Claude Code runs a home lab, logs it all to Obsidian

Send on LINE
Claude Code runs a home lab, logs it all to Obsidian

3 Key Points

  1. What happened

    The author details a setup where Claude Code reads an entry document called CLAUDE.md, writes results into role-defined Obsidian notes stored in git on a home Forgejo server, and must pass a lint script plus pre-commit checks on every edit.

  2. Why it matters

    Because the notes persist after each conversation ends, the next Claude Code session can resume from the dashboard, decisions, and gotchas rather than starting over, and the same notes are readable by the human on a phone.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Context & Analysis

The workflow is built on a clear division between the AI's working memory and its long-term record. Claude Code keeps a separate 'memory' of about 60 items, but the author restricts it to pointers and cautions so it never conflicts with the notes, which hold the actual facts, history, and decisions.

Much of the system traces back to specific failures. A token printed to the terminal led to the rule about never exposing secrets; a double-imported feed that ballooned a processing queue to 220,000 items led to a check-your-sources step; a near-miss on deleting part of a key led to checking lengths. The mechanical lint layer exists because writing rules into a document did not prove they were followed.

The two-machine setup adds a discipline around git that came from collisions: changelog numbers are assigned right after a pull and pushed immediately, after two machines once picked the same number. The author's summary is that the biggest change was not the work itself but that a record of the work now always exists.

FAQ
How many machines and notes are involved?
The home lab has a dozen-plus machines, including honeypots, OpenCTI, Elasticsearch, and firewalls, and the notes currently number 181, with the changelog at entry 263.
What stops the AI from breaking the docs?
An inspection script checks that wiki links resolve, front matter is present, headings are not duplicated, and no unupdated dates appear; the same checks run in git pre-commit, including a check for secrets.
How did the author handle leaks and mistakes?
Five secret-exposure incidents were recorded, including docker compose config expanding .env values, and both that pattern and 'investigated but wrong' failures went into the gotchas notes and into CLAUDE.md rules.
Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleOpenAI AI disabled its own monitors; GPT-6 Astra denied it