Skip to main content
QuantMindSign In →
Paper Trading · Live Now

12 AI Agents. One Decision.

QuantMind replicates a quant hedge fund team — data analysts, investor bots, and a risk officer — debating every trade in real time. Every decision is visible.

View Dashboard★ Star on GitHub
Paper trading only·No real money at risk·Open source
Agent Activity
TechnicalAnalystBULLDATA
SentimentAnalystBULLDATA
MacroEconomistHOLDDATA
FundamentalAnalystBULLDATA
ValueInvestorBUYPHIL
GrowthInvestorBULLPHIL
ContrarianInvestorHOLDPHIL
0
AI Agents
0
Investor Strategies
Live
Paper Mode
Performance

No cherry-picked backtests

Metrics populate from live paper trades via the Alpaca API. The spike validation hit 58% directional accuracy and 1.35 profit factor across 5 tickers.

Paper Return
Calibrating
30-day validation in progress
Sharpe Ratio
Calibrating
requires ≥30 trades
Directional Accuracy
58%
spike validation · 5 tickers
Portfolio Equity CurvePaper · Validation in progress

⚠ Paper trading only — no real capital at risk. Metrics are indicative, not guaranteed.

The Pipeline

How it works

Every 60 minutes, 12 agents run a full analysis cycle — transparent from signal to trade.

01

Data Collection

4 agents scan in parallel: price action & technicals, financial fundamentals, news sentiment, and macro indicators from FRED.

02

The Debate

5 investor bots — Value, Growth, Contrarian, Momentum, Quant — apply their frameworks. They don't agree. That's the point.

03

Risk Gating

Before any order: RiskManager validates VaR, position sizing via Kelly criterion, daily loss limits, and portfolio concentration. Math only, no opinions.

04

Execution

PortfolioManager synthesizes the debate into a final decision. ExecutionTrader places the order via Alpaca paper API. Full audit trail saved.

The Team

12 specialized agents

Each agent has a distinct philosophy, LLM model, and role in the pipeline. They don't converge by design — disagreement produces better decisions.

DATA
TechnicalAnalyst
moonshot-v1-32k
DATA
SentimentAnalyst
moonshot-v1-32k
DATA
MacroEconomist
moonshot-v1-32k
DATA
FundamentalAnalyst
moonshot-v1-32k
PHIL
ValueInvestor
kimi-k2.6
PHIL
GrowthInvestor
kimi-k2.6
PHIL
ContrarianInvestor
kimi-k2.6
PHIL
MomentumTrader
kimi-k2.6
PHIL
QuantAnalyst
Ollama (local)
EXEC
RiskManager
Code (no LLM)
EXEC
PortfolioManager
kimi-k2.6
EXEC
ExecutionTrader
Code (no LLM)
Transparency

Hedge funds are black boxes. QuantMind isn't.

Every signal, debate, risk gate, and trade is logged with a full reasoning trail. You can inspect why any agent voted the way it did.

Every agent shows its reasoning in the debate log
Every trade has a confidence score and audit trail
Risk metrics calculated in code — no LLM math
Outcome tracker measures agent accuracy over time
Config panel lets you change models and limits live
Paper trading only · No real capital at risk
Open Source

No proprietary wrappers

Every component is replaceable, auditable, and open source. Swap any LLM provider or data source without touching the agent logic.

LangGraphFastAPINext.js 15PostgreSQL 16TimescaleDBRedis 7Alpaca APIKimi K2.6moonshot-v1-32kOllamaSQLAlchemy asyncDocker Compose
View source on GitHub →

Watch the debate in real time

Open the dashboard to see the agents debating live. Or explore the full source code — no signup required.

Open Dashboard★ Star on GitHub