Drama Engine: A Framework for Narrative Agents

TL;DR

The Drama Engine addresses the challenge of building narrative-oriented AI agents capable of sustained, context-aware interactions with users by repurposing multi-agent system concepts for storytelling. It introduces a TypeScript framework that orchestrates companions, moods, automatic context summarisation, and dynamic prompt assembly on a model-agnostic back-end, enabling both multi-agent chats and task-based writing assistants. The authors demonstrate two primary applications—A1 multi-agent chat and A2 virtual coworker for creative writing—driven by a deputy-based delegation mechanism and moderator-controlled dialogues. They report qualitative experiences from the Writers Room, discuss limitations related to model size and behavior, and outline future work on memory and tool-calling to enhance autonomy and practicality.

Abstract

This technical report presents the Drama Engine, a novel framework for agentic interaction with large language models designed for narrative purposes. The framework adapts multi-agent system principles to create dynamic, context-aware companions that can develop over time and interact with users and each other. Key features include multi-agent workflows with delegation, dynamic prompt assembly, and model-agnostic design. The Drama Engine introduces unique elements such as companion development, mood systems, and automatic context summarising. It is implemented in TypeScript. The framework's applications include multi-agent chats and virtual co-workers for creative writing. The paper discusses the system's architecture, prompt assembly process, delegation mechanisms, and moderation techniques, as well as potential ethical considerations and future extensions.

Figures (2)

• Figure 1: The control flow of a multi-agent conversation orchestrated by the moderator
• Figure 2: The control flow of a deputised action