📊 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 · TradingAgents is a new project that uses a multi-agent system of LLMs to simulate market decisions and execute paper trades. It extends an existing framework to enable autonomous operation, aiming to test AI decision-making in trading contexts.

Forezai · TradingAgents has been launched as a new open-source project that deploys a committee of large language models (LLMs) to simulate trading decisions through paper trades, marking a step toward AI-driven research in financial decision-making.

The project is a fork of an existing multi-agent research framework that structures LLMs into specialized roles—including analysts, debate agents, risk assessors, and decision-makers—to generate trading signals. The new fork adds operational components such as an autonomous scheduler, paper-trading interfaces, position management, and a web dashboard, enabling continuous, automated testing without risking real money.

Unlike previous experiments that focused on backtested strategies, Forezai · TradingAgents emphasizes real-time simulation and decision logging, facilitating detailed analysis of the reasoning process behind each trade proposal. The system can operate in multiple modes, including local simulation, paper trading via Alpaca, and a shadow mode that compares simulated decisions with live market data, all running locally without cloud data transmission.

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 Market Decision Systems

This development matters because it pushes forward the use of large language models in structured, autonomous market decision-making, moving beyond simple prediction to explainable, multi-voice reasoning. It offers a platform for testing whether AI committees can improve upon random or rule-based strategies in simulated trading environments, which could influence future research in AI and finance.

While the system currently operates only in paper trading mode, its architecture aims to provide insights into how AI agents might support or augment human decision-makers, especially in complex, multi-faceted analysis scenarios. The project also emphasizes transparency and auditability, essential for future applications in real trading environments.

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.

Evolution of AI in Trading and Research Frameworks

Previous research, such as the Polybot experiments, demonstrated that many parametric trading strategies fail to survive real-market conditions, often collapsing after promising backtests. This led researchers to explore less rule-bound approaches, including multi-agent systems of LLMs structured to argue and reason about market data. The TradingAgents framework, originally developed by TauricResearch, exemplifies this approach by assigning distinct roles to different LLMs, fostering explicit reasoning and debate.

Forezai · TradingAgents builds on this foundation by adding operational capabilities, enabling continuous, autonomous testing of the AI committee’s decisions in simulated trading environments. This marks a shift from purely theoretical or backtested research toward practical, real-time experimentation.

“By integrating operational layers into the multi-agent framework, Forezai · TradingAgents enables continuous, autonomous testing of AI decision-making in simulated markets, providing a new tool for research and development.”

— Thorsten Meyer, project lead

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.

Unanswered Questions About AI Trading Decision Quality

It remains unclear how well the AI committee’s decisions will perform in live or more complex market conditions, as the current system is limited to paper trading and simulated environments. The effectiveness of the multi-agent reasoning in generating profitable or even stable strategies has yet to be validated beyond initial experiments.

Furthermore, the extent to which this approach can be scaled or adapted to real trading remains uncertain, especially considering the challenges of market unpredictability and the risks involved in live deployment.

Automated Trading for a Living : Smart Money Concepts & Machine Learning for Forex & Futures Traders, Made Easy (Smart Money Concepts Mechanical Trading Series)

Automated Trading for a Living : Smart Money Concepts & Machine Learning for Forex & Futures Traders, Made Easy (Smart Money Concepts Mechanical Trading Series)

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Next Steps for Testing and Developing AI Market Agents

Future developments include deploying the system in live paper trading environments with more diverse assets, refining the agent roles for better decision quality, and conducting comparative analyses against traditional strategies. Researchers also plan to improve transparency tools and explore how AI decision-making can be integrated into human workflows.

Long-term, the project aims to evaluate whether multi-agent LLM systems can reliably support or enhance human trading decisions, potentially influencing AI research and financial technology development.

Invest Smarter with AI: A Practical Guide to Long-Term Investing, Financial Planning, and Building Wealth

Invest Smarter with AI: A Practical Guide to Long-Term Investing, Financial Planning, and Building Wealth

As an affiliate, we earn on qualifying purchases.

As an affiliate, we earn on qualifying purchases.

Key Questions

Can Forezai · TradingAgents trade with real money?

No, the current system is designed solely for simulated, paper trading environments. It explicitly refuses to execute real trades unless deliberately overridden, which is discouraged for safety reasons.

How does the multi-agent architecture improve decision-making?

By structuring multiple specialized LLMs to argue and reason explicitly about market data, the system aims to produce more balanced and explainable trading signals, reducing reliance on single-model predictions.

Is this system intended to replace human traders?

Not currently. The project is focused on research and testing AI decision-making processes. Its goal is to understand whether AI committees can generate decisions comparable to or better than random strategies in simulated environments.

What are the risks of deploying such AI systems in live trading?

Potential risks include unanticipated decision errors, market volatility, and the inability of the AI to adapt to unforeseen conditions, which could lead to losses if used with real money. Caution and further validation are essential before live deployment.

Will the project be open-source?

Yes, the Forezai · TradingAgents fork is released under the Apache-2.0 license, making it accessible for research and development by the community.

Source: ThorstenMeyerAI.com

This content is for general information only and is not financial, tax or legal advice. Consult a qualified professional for decisions about your money.
You May Also Like

Graceful Debt Collection: What to Do if a Customer Owes Money

Managing overdue accounts gracefully requires balancing assertiveness and professionalism to ensure successful debt recovery.

AI Trading Bot — Week Two: The candidate edge collapsed

The promising BTC fair-value trading strategy failed in its second week, with all tested approaches now showing losses, raising questions about AI trading viability.

Mortgage rates fall to lowest level in over a month as Iran deal framework takes shape

Mortgage rates have fallen to their lowest in over a month as progress on Iran’s nuclear deal framework influences financial markets.

7 Features to Check Before You Buy a POS Cash Drawer

The 7 features to check before buying a POS cash drawer will help you choose the perfect fit—discover what matters most for your store’s needs.