Skip to content
Tech News
← Back to articles

MarketFish – Simulate a market with 128 AI consumers before you launch

read original more articles
Why This Matters

MarketFish introduces a groundbreaking approach for product testing by simulating a digital marketplace with 128 AI consumers, enabling companies to predict market responses before launch. This technology helps reduce risks, optimize product strategies, and better understand consumer behavior through sophisticated multi-agent simulations. Its integration of academic research and multiple LLM providers makes it a powerful tool for the tech industry and consumers alike.

Key Takeaways

🐟 MarketFish

Don't guess. Simulate.

Before you launch, let hundreds of AI consumers vote with their wallets.

MarketFish is a multi-agent market simulation engine. Instead of asking one LLM "will this product succeed?", it builds a digital market with 128+ AI consumers β€” each with their own identity, budget, emotions, and biases β€” and lets them shop across 30 rounds. Their purchase decisions, churn patterns, and social influence reveal what real users would do.

Built on 6 academic papers (Generative Agents, OASIS, TwinMarket, Agent Bazaar, EconSimulacra, SMIF) and 11 LLM providers.

δΈ­ζ–‡ζ–‡ζ‘£

Quick Start

git clone https://github.com/Key-wxh/market-fish.git cd market-fish cp .env.example .env # Edit .env β€” add at least ONE LLM API key (DeepSeek is cheapest) pip install -r requirements.txt streamlit run streamlit_app.py

Open http://localhost:8501 β†’ pick a mode β†’ run.

Screenshots

... continue reading