📊 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 fork of an AI framework that uses a committee of LLMs to simulate trading decisions. It adds operational tools for research but does not enable live trading with real money. This development aims to explore AI decision-making in trading environments.
Forezai · TradingAgents, a new open-source project, has been launched as a fork of an existing multi-agent large language model (LLM) framework designed for simulated trading research. It introduces operational features that enable automated paper-trading, including scheduling, position management, and multi-broker support, while explicitly preventing real-money trading.
The project builds on a framework originally developed by TauricResearch, which structures multiple specialized LLMs to analyze market data and argue their positions. The new fork, Forezai · TradingAgents, adds an operational layer, including an autonomous daily scheduler, a position evaluation system, and a multi-broker abstraction that supports local, paper, and shadow trading modes. It also features a web dashboard for monitoring performance metrics such as equity curves, win rates, and exit reasons. The system does not promise prediction accuracy; instead, it emphasizes explicit reasoning through diverse agent roles, aiming to explore whether collaborative AI can produce at least no worse-than-random trading decisions in simulated environments.AGENTS
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
Analysts · Debate · Risk · Decision
78% / -33%
Polybot prior: fleet win rate
combined with -33% bankroll
combined with -33% bankroll
520+
Passing unit tests across engine,
services, HTTP routes (starting baseline)
services, HTTP routes (starting baseline)
€0 floor
LLM cost on Codex OAuth
(falls back to public API per token)
(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
Implications for AI-Driven Market Research
This development matters because it provides a structured environment to test whether collaborative large language models can generate meaningful trading insights without relying on traditional rule-based strategies. While not designed for real trading, the project advances understanding of AI reasoning, decision-making, and potential applications in quantitative research. It also highlights the importance of transparent, auditable AI processes in financial experimentation, potentially influencing future AI tools for market analysis and strategy development.Amazon
AI trading simulation software
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Background of Multi-Agent AI in Trading Research
Previous research with the original TauricResearch framework demonstrated that parametric, rule-based trading strategies often fail to survive real-market conditions, despite promising backtests. The shift toward multi-agent LLM systems aims to overcome these limitations by leveraging diverse perspectives and explicit reasoning. The initial experiments showed that even a high win rate does not guarantee profitability, emphasizing the complexity of market dynamics. The new project, Forezai · TradingAgents, extends this research by operationalizing the framework for systematic testing, moving beyond theoretical analysis to practical simulation tools.“Forezai · TradingAgents offers a new way to evaluate AI decision-making in trading environments, emphasizing transparency and research utility over live trading. It’s a step toward understanding how collaborative AI can approach market reasoning.”
— Thorsten Meyer, lead researcher
Amazon
paper trading platform with dashboard
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Uncertainties Surrounding AI Trading Efficacy
It remains unclear whether the committee of LLMs in Forezai · TradingAgents can consistently produce decisions that outperform random chance in real or simulated trading environments over extended periods. The framework explicitly does not promise predictive accuracy or profitability, and the effectiveness of such AI systems in live trading scenarios has not yet been tested.
Amazon
multi-agent trading system
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Future Testing and Potential Applications
Next steps include deploying the system in longer-term simulation runs to evaluate stability and decision quality. Researchers plan to analyze the reasoning chains and decision patterns of the agent committee, exploring whether modifications can improve performance. Although the current focus is on research, future iterations may consider controlled live testing with strict safeguards, emphasizing transparency and risk management.
Amazon
automated trading research tools
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
Key Questions
Can Forezai · TradingAgents be used for live trading?
No, the current system is designed solely for paper-trading and research purposes. It explicitly prevents real-money trading to avoid financial risk.
How does the AI committee make trading decisions?
The system routes data through specialized LLM roles—analysts, debate agents, risk teams, and portfolio managers—that articulate their reasoning explicitly. The final decision results from synthesizing these arguments.
What is the main goal of this project?
The primary goal is to evaluate whether collaborative LLM systems can produce at least no worse-than-random trading decisions in simulated environments, advancing understanding of AI reasoning in finance.
Will this project lead to autonomous trading systems?
Not currently. The project emphasizes research, transparency, and understanding AI decision processes. It does not aim to develop autonomous trading bots for live markets at this stage.
What makes Forezai · TradingAgents different from other AI trading tools?
It structures multiple specialized LLMs into a transparent, reasoning-based committee, explicitly articulating decision rationale, rather than relying on single-model predictions or rule-based algorithms.
Source: ThorstenMeyerAI.com
