Forezai publishes open-source instruments for measuring whether trading strategies actually work — one on Polymarket's prediction markets, one on the stock market via LLM multi-agent committees. Built so the data can say "this doesn't work" out loud when it doesn't. Most of the time, it doesn't.
The two projects share a philosophy — paper-trading by default, audit-logged decisions, honest disclaimers, open source — but trade different markets with different machinery.
Multi-experiment paper-trading bot for Polymarket's 5-minute BTC/ETH/SOL/XRP Up/Down markets.
LLM multi-agent stock research with an autonomous paper-trading loop. Fork of TauricResearch/TradingAgents.
Thorsten Meyer is a Munich-based futurist, post-labor economist, and recipient of OpenAI's 10 Billion Token Award. He spent two decades managing €1B+ portfolios in enterprise ICT before deciding that writing about the transition was more useful than managing quarterly slides through it. More at ThorstenMeyerAI.com.
Forezai is the umbrella for several open research projects he publishes. Built independently with the assistance of large-language-model coding tools, then carefully reviewed and shipped under permissive open-source licenses. The shared bias is honesty over hype: when the data says a strategy is failing, the dashboard says so. When a high win rate is just a mechanical illusion, the calibration view explains why.
Companion projects: ThorstenMeyerAI.com (essays on the post-labor transition) and DojoClaw (the AI content engine behind 450+ magazines).
Both projects can lose real money if you flip them to live mode with a funded account or wallet. The default is paper trading. Paper-trading results do not predict live results. The software is provided as is with no warranty. This is research, not investment advice.