Launched this week
Parastore
Simulate real store with LLM-powered synthetic consumer
82 followers
Simulate real store with LLM-powered synthetic consumer
82 followers
Parastore is an open-source (MIT) retail simulation where LLM-powered synthetic consumers walk through a 3D virtual store, browse shelves, and make purchase decisions. Each consumer follows one of 12 behavioral patterns with grammar-constrained actions, randomized context (mood, budget, company), and impulse-buy logic triggered by what they see along their route. Validated against real POS data with 0.955 Spearman correlation. Python/FastAPI + React/Three.js. Any LLM backend.
Parastore
@kjlis We haven't really seen any unconventional or weird behavior yet—they’ve been staying surprisingly human-like. 😂
mailX by mailwarm
How much freedom do you give them, like can they compare prices and brands or is it mostly choose and buy?
@othman_katim They actually do compare prices and brands before deciding. 👻
Stripo.email
This is honestly one of the more interesting AI simulation projects I’ve seen lately. Synthetic shoppers with mood, budget, impulse buying, and route-based decisions feels weirdly realistic. Congrats on the launch!
@alina_tyslenok_ Thanks so much, glad you found it interesting!