Multiplayer AI on the Edge

Learn how to build persistent, reactive AI assistants using Maggie Appleton’s AI Daemons design, deployed on Cloudflare Workers with Durable Objects for server‑push, stateful LLM workflows.

Overview

There are two kinds of AI assistants:

Ones that you have to ask to do things.
Ones that watch everything you do in the background and act on your behalf for you

I implemented Maggie Appleton’s “AI Daemons” design concept, with her permission, from https://maggieappleton.com/lm-sketchbook#daemons. This demo shows how I built it, and deployed it to the edge using Cloudflare Workers platform.

Video

Links

https://github.com/jevakallio/party-daemons
This project implements AI Daemons using Partykit, a real-time serverless platform.
https://maggieappleton.com/lm-sketchbook
Sketches non-chatbot language model interfaces for epistemic reasoning and ideation.

Tech stack