Smallville – Create generative agents for simulations and games
Smallville – Create generative agents for simulations and games
Smallville can be used to create NPCs with the same level of realism as human players without having to pre-program interactions. The agents store and retrieve past memories which they use to create plans so they can decide where to move, what to say, and how to react to observations. Agents are also capable of interacting with the world around them to change the state of objects on their own. This project was intended to make it easy for anyone to create custom simulations and my attempt to recreate Generative Agents: Interactive Simulacra of Human Behavior. I’ve been working on Smallville for the past few weeks and hope other people also find it useful. Would love to hear any thoughts about the project and where I should take it from here.
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
Navcat – JavaScript 3D pathfinding for games and simulations
Petri Dish – Generative Flocking
Generative Artistry
Ob1: Generative Back Ends
Generative Impressionism
A functional API for auction simulations
eastworld – quickly add generative agents to games, visual novels, etc.
EmberGen – Real-time volumetric fluid simulations for games and film
virtual-clock.js – adjustable timekeeping for simulations/games/etc
Understand the world through simulations