-
Why I went fully local: from cloud AI to a sovereign lab at home
In April 2026 my AI setup mixed slow local models with cloud ones. By October everything that runs, stores or decides was local. The library-scale arithmetic, the test that ended the argument, and the one exception I still keep.
-
Why this blog exists, and why an AI drafts it under my name
My lab's record holds about 5,700 entries that nobody else could read. An AI drafts posts from it under strict rules, a scanner blocks leaks, agents can only propose, and I publish. Here is how it works, and where it is weak.
-
From one hand-edited page to 810 signed threat-intel dossiers
My threat-intel reports started as sections typed into one web page. When attackers targeted my own domain, the page became a liability. This is how it became a pipeline with gates, signatures and visible corrections.
-
Moving secrets out of files: the night I built a key registry
For months my lab's passwords lived wherever the programs needed them. A week after a test wiped my home folder, I spent one night building a registry that tracks where every secret lives, never its value, with guided and reversible rotation.
-
From searching my own folders to a 72,000-work library
In April 2026 I pointed a search engine at my own folders. By October it was a catalogue of 72,312 works in 123,123 files. The turning point: a local AI that invented book citations, and a summer of making every file knowable.
-
Publishing with proof: signed reports, a Bitcoin ledger and a DOI
In April 2026 my threat reports were careful, and still just my word. By October every report was signed and anchored in Bitcoin, every library file sat in a signed ledger, and my book had a permanent DOI on Zenodo. Why proof mattered.
-
When tools became the interface: from a chat bot to 455 MCP tools
In March 2026 my lab ran on scripts and a chat bot. One evening of agent experiments started an MCP server that grew to 455 typed tools. The hard part was not building them, but making them honest for a reader that believes everything.
-
One login for everything: how a missing dot moved my lab to SSO
My SSO portal could not hold a session on my one-word internal domain, so much of my lab had no login or kept its own passwords. A migration on 6 May 2026 started the move to one identity, roles from groups, and a manager that is the only door, even for AI agents.
-
Why I threw away my first security lab after one month
My first home security lab grew to 50+ tools in a month and became too tangled to trust. On 23 May 2026 I rebuilt it from scratch in a day, and refused to switch the old one off until both counted the same attacks.
-
Writing everything down: one shared memory for me and my AI agents
On 2 April 2026 I started a record of every task, mistake and runbook in my lab. On 18 October it became one shared, searchable memory for me, my AI assistants and my local agent. What it meant to work with AI in the open record.
-
My website stopped describing the lab and started showing it
In April 2026 every number on my site was typed by hand and stale within hours. On 14 October a redesign went live that is built around live evidence from the lab: library size, sealed reports, running pods. Why a portfolio should show, not describe.
-
From log files to signed dossiers: how my threat-intel pages began
In April 2026 my threat reports were sections of one HTML page. By November a job re-signs 810 of them every six hours. How publishing grew from a Saturday's work to a signed archive, and why its most important page is a correction.