Parastore

Simulate real store with LLM-powered synthetic consumer

90 followers

Simulate real store with LLM-powered synthetic consumer

90 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 Alternatives

Exploring Parastore? Compare it with Langfuse for open-source LLM observability, Tiledesk to launch chatbots and conversational apps, and Camel AGI for multi-agent collaboration—great complements or alternatives for testing retail flows with synthetic shoppers.