# GenWorlds

A discontinued event-based framework for building multi-agent systems, where AI agents communicate asynchronously over a websocket and interact with shared objects in a customizable environment.

GenWorlds is an event-based communication framework for building multi-agent systems, where AI agents interact asynchronously with each other and with objects in a customizable environment over a websocket connection. The project is discontinued in favor of a successor project from the same team.

It draws on the "Generative Agents: Interactive Simulacra of Human Behavior" research paper, providing goal-oriented agents built on LangChain that can be extended to simulate complex behavior, shared objects that agents can interact with to reach their goals, and memory management so agents store, recall and learn from past experience.

It is built on OpenAI's GPT API, LangChain and Qdrant, and was inspired by AutoGPT.

Website: https://github.com/genlayerlabs/genworlds