📊 Full opportunity report: Introducing Forezai · TradingAgents — a committee of LLMs decides paper-trades on ThorstenMeyerAI.com — validation score, market gap, and execution plan.

TL;DR

Forezai has launched TradingAgents, a framework where multiple LLMs collaborate in structured roles to make simulated trading decisions. This development aims to explore AI’s potential in market analysis beyond rule-based strategies, with operational tools added for research purposes.

Forezai has launched TradingAgents, a system where a committee of specialized large language models (LLMs) collaboratively generate paper-trading decisions. This development aims to test whether AI can outperform random choice in simulated markets by leveraging structured debate and reasoning among models. The system is designed for research, not live trading, and includes operational tools for automation and monitoring.

The TradingAgents framework is a fork of an open-source multi-agent research project that uses LLMs in distinct roles—analysts, debate agents, risk assessors, and decision-makers—to evaluate stock or market data. Unlike simple prediction models, it emphasizes explicit reasoning and argumentation among models, which are structured to produce comprehensive trading proposals.

Forezai’s version adds operational features: an autonomous scheduler runs the system daily, generating paper orders with filtering and risk controls; a position manager evaluates trades for exit points; and a multi-broker abstraction supports simulation with local, paper, or parallel modes. A web dashboard provides real-time insights into performance metrics, all running locally without cloud data transfer.

This setup does not trade with real money unless deliberately overridden by the operator, ensuring a research-oriented environment. The project aims to assess whether AI-driven committees can produce decisions at least as good as random chance after fees, based on structured argumentation rather than prediction accuracy alone.

Introducing Forezai · TradingAgents — Thorsten Meyer AI
AGENTS
● ANNOUNCEMENT / MAY 2026
THORSTEN MEYER AI · FOREZAI · § 03
FOREZAI · 03
TRADINGAGENTS · LAUNCH
Research Series · Companion to Polybot Week 1-2 · 2026-05-17

Introducing Forezai · TradingAgents.
A committee of LLMs
decides paper-trades.

After two weeks of finding out most parametric strategies don’t work, the obvious next research question: can multi-agent LLM judgment do any better?
A fork of the open-source TradingAgents framework (TauricResearch): thirteen LLM agents in four stages — four parallel analysts · a bull-bear debate with research-manager arbitration · a three-voice risk team · a two-layer trader + portfolio-manager decision. The fork keeps the agent graph intact and adds the operational layer the upstream doesn’t ship: an autonomous loop · a multi-broker abstraction · a local web dashboard · Codex OAuth · MCP plug-ins · 520+ unit tests. The question is narrower than “do LLMs predict the market” — that prior is “no, with high confidence.” The narrower question is: when LLMs are structured into specialised adversarial roles, does the committee produce decisions at least no worse than a coin flip after fees? Honest priors before running: it might fail too. If it appears to work, the most likely explanation is variance.
This is not financial advice. Nothing in this announcement should be used to inform real trading decisions. The software described trades simulated money by default. If you reconfigure it to trade real money, you should expect to lose that money — regardless of how clever any individual agent’s reasoning looks. Algorithmic trading is zero-sum after fees and structurally hostile to part-time retail strategies.
13 agents
Specialised roles in four stages
Analysts · Debate · Risk · Decision
78% / -33%
Polybot prior: fleet win rate
combined with -33% bankroll
520+
Passing unit tests across engine,
services, HTTP routes (starting baseline)
€0 floor
LLM cost on Codex OAuth
(falls back to public API per token)
FOREZAI / TRADINGAGENTS· APACHE 2.0 FORK· UPSTREAM TAURIC RESEARCH· LANGGRAPH· 13 AGENTS / 4 STAGES· 4 PARALLEL ANALYSTS· BULL-BEAR DEBATE· 3-VOICE RISK TEAM· TRADER + PORTFOLIO MANAGER· 5-TIER FINAL RATING· ALPACA PAPER + LOCAL + SHADOW· LIVE ENDPOINTS HARD-REFUSED· FASTAPI + REACT VIA CDN· CODEX OAUTH· MCP PLUG-IN REGISTRY· 520+ UNIT TESTS· POLYBOT WEEK 1: 21 EXPERIMENTS· WEEK 2: -33% BANKROLL· 78% FLEET WIN RATE· HONEST RESEARCH, NOT EDGE· FOREZAI / TRADINGAGENTS· APACHE 2.0 FORK· UPSTREAM TAURIC RESEARCH· LANGGRAPH· 13 AGENTS / 4 STAGES· 4 PARALLEL ANALYSTS· BULL-BEAR DEBATE· 3-VOICE RISK TEAM· TRADER + PORTFOLIO MANAGER· 5-TIER FINAL RATING· ALPACA PAPER + LOCAL + SHADOW· LIVE ENDPOINTS HARD-REFUSED· FASTAPI + REACT VIA CDN· CODEX OAUTH· MCP PLUG-IN REGISTRY· 520+ UNIT TESTS· POLYBOT WEEK 1: 21 EXPERIMENTS· WEEK 2: -33% BANKROLL· 78% FLEET WIN RATE· HONEST RESEARCH, NOT EDGE·
FIG. 01 — THE 13-AGENT COMMITTEE
Thirteen specialised roles · four stages · biases made to argue in public
The architecture forces the system to articulate its reasoning rather than relying on what a single context window happens to recall
Stage 1 · Four analysts in parallel4 agents
Market
Structure, ranges, regime indicators
News + Insider
News flow, filings, insider activity
Fundamentals
Balance sheet, earnings, ratios
Social Sentiment
Social-media tone, retail signal
Stage 2 · Bull-bear debate + research-manager arbitration3 agents
Bull researcher
Argues upside thesis from analyst reports
Bear researcher
Argues downside thesis from same reports
Research manager
Arbitrates · writes single synthesis
Stage 3 · Three-voice risk team3 agents
Aggressive
Looks for upside · accepts variance
Conservative
Looks for downside · protects capital
Neutral
Balances · forces downside articulation
Stage 4 · Two-layer decision2 agents
Trader
Three-tier proposal · buy / hold / sell
Portfolio manager
Five-tier rating + price target + horizon · sees arguments only, never raw data
The portfolio manager only sees the arguments, never the raw data — which forces the committee to make its reasoning explicit rather than relying on a single context window’s recall. The upstream framework ships the agent graph; it does not ship the operational machinery to run that graph on autopilot, observe its results honestly, store them for later inspection, or prevent the operator from accidentally trading real money. That gap is what the Forezai fork fills.
FIG. 02 — THE POLYBOT PRIOR · WHY THIS IS A DIFFERENT BET
Two weeks of paper-trading prediction markets · the trap underneath the headline numbers
25 experiments · 78% fleet-wide win rate · -33% bankroll · most parametric strategies are structurally negative-expectation when measured honestly
The flattering number
78%
Fleet-wide win rate · week 2
“You can win four out of five trades and still go broke, because the one loss is bigger than the four wins put together.” Win rate without P&L context is a mechanical illusion.
The honest number
−33%
Fleet bankroll · week 2 close
The strongest possible demonstration of the trap. A parametric trading strategy that looks compelling in a backtest will almost always fail to survive a fresh sample. Most “edges” are mechanical artefacts.
Week 1: 21 parallel strategy experiments · early winners mostly mechanical illusions · exactly one strategy (a fair-value taker on BTC) showed the mathematical signature of real edge over a few hundred settled trades. Week 2: same fair-value strategy with more data collapsed. A separate mid-week hypothesis (market-making) also failed cleanly. Fleet ended week 2 at roughly negative thirty-three percent of bankroll. The honest research finding wasn’t on the winning side — it was on the losing side. Adding more parameters to Polybot wouldn’t change that. TradingAgents is asking a separable question.
FIG. 03 — WHAT THE FORK ADDS · THE OPERATIONAL LAYER
Six layers the upstream framework doesn’t ship
Same agent graph, intact. The fork makes it a research instrument rather than a tech demo.
01 · Loop
An autonomous loop
Scheduler · watchlist · auto-trader maps ratings to paper orders · allow-list filtering · per-ticker cooldowns · sector caps · cash checks · position manager evaluates open positions every 60s for TP / SL / max-hold. Append-only audit logs.
02 · Brokers
Multi-broker abstraction
Three modes: local Python broker (yfinance fills, JSON-persisted) · Alpaca paper-trading adapter · “shadow” mode running both in parallel with divergence view. Real Alpaca live endpoints are hard-refused at multiple layers.
03 · Dashboard
A local web dashboard
FastAPI backend · React via CDN, no Node toolchain · SVG equity curve · rolling-peak drawdown · win-rate by rating / ticker / model · exit-reason breakdown · LLM cost vs realised P&L joined by run ID. Runs locally; nothing sent to a cloud service.
04 · Codex
Codex OAuth
Runs the engine on a ChatGPT Pro subscription via the Codex backend. LLM cost floor effectively zero if you already have ChatGPT Pro. Token stored encrypted locally. Falls back to the regular OpenAI API if you’d rather pay per token.
05 · Alerts
Multi-channel alerts
Slack · Discord · SMTP email · configurable filter on rating events and order fills · append-only history kept locally. Webhook URLs masked in API responses so a screenshot can’t accidentally leak credentials.
06 · MCP
MCP plug-ins
Registry for adding Anthropic Model Context Protocol servers (Kensho · Aiera · FactSet · Morningstar · LSEG) as analyst tools. Plug-ins advertise category (fundamentals · news · market data · social) · probe endpoint tests credentials.
Honest-by-design touches: every generated report prepends “Research, not advice” and appends a footer with version, commit, provider, models used, run ID, and cost. Closed trades carry the same metadata. 520+ passing unit tests across engine, services, and HTTP routes. The intent: when the system loses money, the journal makes it impossible to pretend it didn’t.
FIG. 04 — HONEST PRIORS · BEFORE RUNNING THIS IN ANGER
Three priors stated before the data starts arriving
The bias of the project: when the data says no, the dashboard says no, the article says no
1
It might fail too. LLMs are not oracles, and a sophisticated framework around language-model outputs does not change the underlying error rate of the model. Sample is still everything. The framework’s outputs are subject to the same statistical noise as any prediction system over small samples.
Highest likelihood
2
If it appears to work, the most likely explanation is variance. The same trap that caught the first article’s candidate edge applies here. A high win rate over fifty trades means much less than it looks. Without out-of-sample confirmation, a flattering early sample tells you almost nothing about whether the system has real edge.
Second-most likely
3
If it appears to work for the right reasons — empirical win rate matches stated confidence, and alpha-versus-benchmark persists across non-overlapping samples — that would be a meaningful research finding. Whether that happens, I don’t know. The point of putting it in the open is that the data will say.
Genuinely open
This is explicitly not a launch announcement for a product anyone should connect a real brokerage account to. The Alpaca live endpoints are hard-refused at multiple layers in the code, and the design choice is deliberate. The right next step is data, not deployment. The bias of the whole project is straightforward: when the data says no, the dashboard says no, the article says no, and no one tries to retroactively rescue the thesis. That’s the contribution.
FIG. 05 — WEEK THREE · WHAT THE METHODOLOGY WILL MEASURE
Four concrete measurements before publishing findings
The hope: write the week-three article from a position of “here’s what the data says”. The fear: another candidate falsified at higher sample. Both outcomes are publishable.
M1 · Sample discipline
Small watchlist for a few weeks before publishing
A handful of tickers across two or three sectors. Long enough to gather sample, narrow enough to keep attention on what’s actually happening per agent. Avoid the noise of a 65-ticker autonomous loop until the smaller version has been read carefully.
M2 · Calibration view
Stated confidence vs. realised win rate
When the system says “75% confident”, do the trades actually win 75% of the time? Same measurement applied to Polybot’s fair-value model. If the model is systematically over-confident, that bias dominates everything downstream.
M3 · Cost accounting
Cost per ticker · per rating · per profitable trade
With Codex OAuth the marginal LLM cost is effectively zero. With the public OpenAI API, each run is hundreds of agent turns. The honest question: does this scale economically if you ever did run it at real cost?
M4 · Non-overlapping windows
Alpha vs benchmark · out-of-sample
Not within-sample alpha — trivially inflatable. Hold out one period entirely, run the system on the next, then check whether the held-out result matches the in-sample stats. If they diverge sharply, the in-sample was curve-fit.
Open under Apache-2.0 with upstream cited from every relevant surface. Not open: the operator’s running results, the specific watchlist, the per-agent prompt customisations, the alert channels, the trade journals — kept local for the same reason Polybot’s per-experiment data is kept local. Publishing exact configurations encourages people to copy them with real money, which is the opposite of what an honest research project should do. Summary findings will be published. Recipes will not.
The bet is on a different mechanism, not a different parameter setting. The point is not to find a money-printing AI. The point is to put honest measurements of these systems into the public record — so the next person looking at the space starts a step further along than the last.
Thorsten Meyer AI · Introducing Forezai · TradingAgents · § 03

Potential Impact of AI-Driven Trading Committees

This development is significant because it explores a novel approach to market decision-making, moving beyond traditional rule-based or predictive models. If successful, it could demonstrate that structured reasoning among multiple AI agents can generate robust trading strategies in simulated environments, informing future research and possibly influencing automated trading systems.

While the system currently operates in a research context, its design emphasizes transparency, explicit reasoning, and modularity, making it a valuable tool for understanding AI’s capabilities and limitations in financial decision-making. It also highlights the importance of operational infrastructure in transitioning AI research from theory to practical experimentation.

Mastering the Art of Equity Trading Through Simulation, + Web-Based Software: The TraderEx Course (Wiley Trading)

Mastering the Art of Equity Trading Through Simulation, + Web-Based Software: The TraderEx Course (Wiley Trading)

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Evolution of AI in Market Simulation and Research

Previous research with parametric trading strategies revealed their fragility, often failing in live simulations despite promising backtests. This prompted questions about whether less rule-bound, more reasoning-based AI approaches could perform better. The original multi-agent framework, developed by TauricResearch and hosted on LangGraph, demonstrated how specialized roles and argumentation could be used to evaluate market data without relying on prediction models.

Forezai’s fork builds upon this foundation by adding operational capabilities, enabling systematic testing and monitoring of AI-driven trading decisions in a controlled environment. This marks a step toward more sophisticated AI research, integrating reasoning, debate, and operational testing in financial markets.

“Our goal with TradingAgents is to see if structured AI committees can produce decisions that are at least no worse than random, providing a foundation for future research into AI-driven market strategies.”

— Thorsten Meyer, Forezai project lead

The Intelligent AI Investor: A Beginner’s Guide to Using AI Tools for Informed Investment Decisions, Risk Management, and Wealth Building (Trading & Investing Series Book 7)

The Intelligent AI Investor: A Beginner’s Guide to Using AI Tools for Informed Investment Decisions, Risk Management, and Wealth Building (Trading & Investing Series Book 7)

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Unclear Performance and Future Validation Steps

It remains uncertain how well the TradingAgents system will perform in extended testing or real-market conditions, as current results are based on paper trading and simulated environments. The effectiveness of the committee approach compared to traditional models or human traders has yet to be validated through rigorous, long-term experiments.

Additionally, the potential for this system to be adapted for live trading or integrated into existing financial infrastructures is still undefined, and operational challenges or risks have not been fully explored.

The No-BS Guide to AI for Trading & Market Research: How to Use ChatGPT, Claude & AI Tools for Market Analysis, Stock Research & Data-Driven Trading ... ... Required (The No-BS AI Playbooks Book 3)

The No-BS Guide to AI for Trading & Market Research: How to Use ChatGPT, Claude & AI Tools for Market Analysis, Stock Research & Data-Driven Trading … … Required (The No-BS AI Playbooks Book 3)

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Next Steps for Testing and Development

Forezai plans to conduct systematic testing of the TradingAgents framework over longer periods and across different market scenarios to evaluate robustness. Further development will focus on refining the reasoning mechanisms, improving operational stability, and exploring integration with live trading environments under strict risk controls.

Research outputs, including performance logs and decision rationales, will be published to assess the AI committee’s decision quality and inform future enhancements.

3-Tier Foldable Paper Display Stand - Portable Adjustable Showcase for Trade Shows, Cosmetics & Handbags, Retail Merchandising Platform for Boutique, Exhibitions (L197 in * W31.5 in * H46 in)

3-Tier Foldable Paper Display Stand – Portable Adjustable Showcase for Trade Shows, Cosmetics & Handbags, Retail Merchandising Platform for Boutique, Exhibitions (L197 in * W31.5 in * H46 in)

Certified Kraft Paper & Honeycomb Bionic Technology deliver exceptional structural integrity – ensuring even load distribution, sustained operational…

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Key Questions

Can TradingAgents be used for real trading now?

No, the current system is designed for research and paper trading only. It does not trade with real money unless deliberately overridden, which is not recommended at this stage.

How does TradingAgents differ from traditional AI trading models?

Unlike predictive models, TradingAgents emphasizes explicit reasoning and debate among multiple specialized LLMs, structured to articulate their arguments and decisions rather than simply forecast market movements.

What are the main operational features added in Forezai’s fork?

The system includes an autonomous scheduler, automated paper trading with filtering and risk controls, a position management module, multiple broker modes for simulation, and a web dashboard for real-time monitoring.

What are the main uncertainties about this project?

Its long-term effectiveness, scalability, and potential for live trading remain untested. The performance in extended or real-world scenarios is still unknown.

What is the ultimate goal of this research?

To determine whether structured AI committees can generate robust, explainable trading decisions, paving the way for future AI applications in automated finance.

Source: ThorstenMeyerAI.com

You May Also Like

Why OCR Is a Bigger Deal Than Most Students Realize

Knowing the power of OCR can revolutionize your study habits, but are you ready to unlock its full potential? Discover how it can transform your learning!

How to Future-Proof a Laptop for Four Years of Statistics Classes

How to future-proof a laptop for four years of statistics classes hinges on key specifications and strategic choices—discover what you need to excel!

The Best Online Courses for Learning Statistics

The best online courses for learning statistics can transform your skills—discover which options are right for you and start your journey today.

Threlmark: Disk Is the Contract

Threlmark launches a new approach where the roadmap is a plain JSON file on disk, enabling open, interoperable, and durable planning tools.