Rduffy

Quên went deeper on memory trust. My SRE lens exposed the next question: when is an agent safe and authorised to act in production?

How a home-lab AI console grew from a viewer into an instrument panel: live knowledge maps, review coverage, writable ideas, voice capture, supervised agent sessions, approvals, and read-only terminal access.

A Thursday where the platform was already noisy before the console existed: vLLM admission failures, indexer livelock, a retired arch-review pipeline, YouTube ingestion, frontmatter corruption, and the first review-tracker cockpit.

After the first agent audit, I had to give the vault, the agent config, and the memory graph the same custody I expect from production code.

After the overnight audit found 173 de-duplicated bugs, the next job was proving the fixes held in production, catching a benchmark that lied, and writing down what changed.

Most agent-memory demos prove they can remember a name. I built one that forgets on purpose - and measured it, including where it falls short.

Season 4 opens with a dynamic workflow that sent 23 slices / 46 agent roles through finder-verifier audit work, paused for usage limits, resumed, and came back with 173 de-duplicated bugs.

A month where I tore the platform's repository down to the studs and rebuilt it as a 16-package workspace without ever letting main break - while restoring a CI pipeline that had been silently dead for four days, fighting a month-long embedding-vs-GPU con

I rebuilt rduffy.uk into one design system and published 20 of my 77 architecture decision records - a sortable, filterable decision log with the context, the call, and what each cost. Here's what's actually new, plus the one idea that ties it together.

A weighted token-budget governor for Claude Code + Codex - and how I found it was metering a number Anthropic never confirmed. Plus: the loop is a token trap.