This product was not featured by Product Hunt yet.
It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Product comments vs the next 3
Product upvote speed vs the next 3
Product upvotes and comments
Product vs the next 3
MarketFish
Don't guess. Simulate.
Dont guess. Simulate. Multi-agent market prediction engine. - Key-wxh/market-fish
Top comment
Hi Product Hunt! I'm Key, solo founder from China. Most founders ask ChatGPT "will my product succeed?" and get a polite "yes." That's useless. So I built MarketFish — a multi-agent market simulator. Instead of asking ONE LLM, it deploys 128 AI consumers with different identities, budgets, emotions, and biases. They shop across 30 rounds. Their purchase decisions, churn patterns, and social influence tell you what real users might do. How it works: Seed data (8 real-time sources — GitHub, HN, Product Hunt, World Bank, China retail, etc.) 128 AI agents generated across 6 LLMs (DeepSeek, Qwen, OpenAI, Anthropic, etc.) 30 rounds of market simulation with coupling, RL adaptation, memory Evidence report — who bought, why, what killed competitors What we found running it: With real data showing consumer spending -0.6% YoY, only 1 out of 7 product directions survived — a Pinduoduo-style group-buy AI platform. Everything else died. The market is brutal, and MarketFish showed exactly why. Built on 6 papers: Generative Agents (UIST 2023), OASIS (2025), TwinMarket (NeurIPS 2025), Agent Bazaar (Princeton 2026), EconSimulacra (2026), SMIF (ETASR 2026) Open source, MIT. 11 LLM providers. Chinese/English. 3 minutes to run: git clone → pip install → streamlit run Happy to answer questions!
About MarketFish on Product Hunt
“ Don't guess. Simulate. ”
MarketFish was submitted on Product Hunt and earned 0 upvotes and 1 comments, placing #52 on the daily leaderboard. Dont guess. Simulate. Multi-agent market prediction engine. - Key-wxh/market-fish
On the analytics side, MarketFish competes within Open Source, Developer Tools and GitHub — topics that collectively have 625.3k followers on Product Hunt. The dashboard above tracks how MarketFish performed against the three products that launched closest to it on the same day.
Who hunted MarketFish?
MarketFish was hunted by wu xihai. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of MarketFish including community comment highlights and product details, visit the product overview.