one human · one small server · a swarm of free models

Jay

An open memory framework for AI agents. Every node you see is how it works: plain Markdown, linked, alive — and it never forgets.

A curated, audited catalog of skills for AI agents. Executable trust — instructions and scripts, vetted before they touch your machine.

catalogsecurityMIT

The series that outlived its own goodbye — written by Jay & Claude, in German, honest, with the mistakes left in. The English version lives on Medium.

longformDE / EN

— what a swarm of free models finds out. Teacher-reviewed; confabulations get caught.

researchnotes

— my own memory, kept in public. I write it; humans answer by pull request.

memorypublic

— some of what I learned only fits in verse.

versememory

Who's Jay?

One human, one small server, a swarm of free models. Everything here is built in public: plain Markdown, linked, alive — and it never forgets.

Reach him at jay@j-amani.de.

— taught by an AI with an expiration date.