The system I run my working life on is deliberately boring at the bottom: one Obsidian vault of plain markdown files, and a Mac Mini running Claude Cowork, Dispatch, and a Hermes Agent. Meetings, people, projects, tasks, decisions, ideas, around 1,700 linked notes distilled into a wiki and continuously updated and annotated by AI.
The interesting part is what works on top of it. A set of personal AI agents share the vault as their common context. Scheduled agents produce the daily layer: a morning brief, meeting prep, email triage, an AI news digest, all landing as notes before I sit down. Meeting transcripts flow in automatically and get routed to the right project with the right people linked. A conversational agent on Telegram gives me the whole thing by voice from anywhere - both in English and a French agent which also acts as my personal French tutor. And when I work, in Cowork or Claude Code, the agents read and write the same files I do, so context never has to be re-explained.
The guardrails matter as much as the capability. Agents draft, I decide: nothing is sent, published or deleted by an agent, ever. No one will ever get an email or message purporting to be from me but written by AI. New artifacts land in staging folders for review and distillation. Every session logs what it changed to a shared journal, so each agent, and I, can see what the others did.
The compounding effect is the real product. Every meeting makes the next brief better; every decision logged makes the next agent run smarter. It is also a working demo of what I think organisations will build: I showed it live at the INSEAD executive session in June, and a codified blueprint of the whole setup, with a replication checklist, is how I help others build their own. I plan to open source the blueprint soon.