LLMday

Large Language Models, Agents & AI Systems

October 1, 2026 San Francisco, California, US

1
Day
20+
Speakers
2
Tracks
100+
Attendees

Claude Opus as a Tabletop Roleplaying GamesMaster for the Mythras Imperative Rule Set

Gully Burns
Altos Labs
Abstract

Roleplaying games are a natural fit for large language models (LLM), allowing them to assume the role of a narrator for a human user navigating an imaginary scenario. Without rules or memory, playing such a game degrades quickly as the LLM drifts, creates arbitrary outcomes with no tension, or misremembers details. Here, I will describe a Claude Skill that acts as a GamesMaster (GM) in a tabletop roleplaying game. Every action, encounter, conversation and item lives in a TypeDB database behind a 66-command CLI, so that the game is driven directly from this narrative state data. The system plays Mythras Imperative and Classic Fantasy Imperative — an openly-licensed (ORC) d100 system. The game is modeled as three layers: (A) universal rules; (B) a living world of NPC agendas on progress clocks producing beats scheduled against a world clock; and (C) epistemics, where each character's knowledge is a projection of data from a single source. True to form, success within the game must be determined through dice rolls so that gameplay is intrinsically stochastic and unpredictable. I will describe the system, and describe some gameplay experiences. The system could have applications to world modeling in non-gaming domains. For some players, RPGs provide a compelling experience of being transported into a story. I argue that the creative capabilities of LLMs combined with the scale of representation made possible by this type of agentic memory could support an entirely new type of gaming experience that transcends the capabilities of human-based TTRPGs.

Bio

Gully Burns is a Staff ML Scientist at Altos Labs, specializing in agentic curation and knowledge engineering to make cellular rejuvenation possible. He has 25+ years experience in the field spanning an Oxford PhD, USC’s ISI, and CZI (now bi[o]hub). He built Skillful-Alhazen, an open biocuration system based on agentic ‘ontological notebook memory’. A lifelong writer and tabletop role-player, in his spare time, he is exploring how AI systems can effectively GamesMaster (GM) traditional tabletop roleplaying games in a way that could provide insight into both world modeling and storytelling.

Sponsors & Partners

Want to become a sponsor? Get in touch!
Let's talk!
We'll email you and share prospectuses for relevant events.
We'd like to (one or more)
Pick at least one
Conferences (one or more)
Pick at least one
Regions (one or more)
Pick at least one
Budget
Pick one