Piggy is an autonomous trading agent that learns from the full spectrum of market patterns — price, volume, volatility regimes, macro context, sentiment — and adapts its strategy to the market it's actually in. Built like a piggy bank: disciplined deposits, compounded patiently, opened only when the maths agree.
Most "AI trading" tools train on one signal — usually news sentiment — and hope it generalises. Piggy treats sentiment as one input among many, alongside the price action, statistical structure, regime context and macro backdrop that actually drive moves.
Candlestick shapes, classical chart patterns, support & resistance, volume profile, breakouts — read continuously across every timeframe from one minute to one week.
Mean reversion, momentum factors, cointegration for pairs, volatility term structure — the quantitative scaffolding behind every disciplined trading book.
Trend / chop, low-vol / high-vol, risk-on / risk-off, correlation regimes, liquidity regimes — Piggy knows which world it's in before it picks a strategy.
What gold, oil, bonds, the dollar index and the VIX are doing right now — and how that historically rhymes with what your instrument is about to do next.
Economic cycles, rate cycles, central-bank policy stance, commitments-of-traders positioning, large-fund flows, event calendars — the slow currents underneath the noise.
News tone, social mood, options flow — read as one input among many, never as the whole story. Sentiment is a tilt, not a thesis.
Rule-based bots commit to one playbook and break the moment the regime changes. Piggy is a meta-controller — it learns which kind of market favours which kind of strategy, then allocates capital between them in real time.
A strategy is only as good as the size you trade it at. Piggy sizes every position by volatility, by edge, and by how much it correlates with what's already on the book.
Position scaled to expected edge — bigger when conviction is high, smaller when it isn't.
Risk-equalised across instruments so a quiet bond pair and a wild crypto pair don't size the same.
If two positions are quietly the same trade, the book knows — and trims one before drawdown does it for you.
Every strategy that ships through Piggy passes walk-forward validation against years of out-of-sample data. These are the bars we require before any capital — paper or real — goes near a model.
Targets reflect Piggy's internal acceptance criteria. Past simulated performance is not a guarantee of future results. Trading involves risk of loss.
You're playing the long game, not the lottery. You want a system that adds small, repeatable edges to the same book — month after month, regime after regime.
Small books, lean teams — you want one adaptive system covering several strategy mandates instead of hiring six PMs.
You want a clean reinforcement-learning testbed with real market data, regime detection and a position-sizing layer that isn't an afterthought.
We're onboarding a small group of beta users through 2026. Tell us what you trade and we'll let you know when a seat opens.