Your workspace runs on your computer.
The Windows research service opens an authenticated browser interface. Strategies, data and results stay in the local application workspace.
AI strategy generation. Local research.
From investment idea to auditable strategy.
Describe the thesis. Generate visible Python. Test it with realistic portfolio accounting — all from the OryxQuant workspace running on your Windows computer.
Research objective Local workspace
Build a diversified equity strategy with explicit risk controls and an auditable rebalance process.
One research loop
The workspace between an investment thesis and a decision.
OryxQuant brings strategy generation, realistic testing, portfolio construction, market data and audit lines into one coherent local workflow.
01 / AI Research
Start with the question, not the boilerplate.
Explain the behavior you want to investigate. Your configured LLM provider turns the objective into strategy candidates while OryxQuant keeps the resulting Python visible for review.
- GenerateTurn a plain-language objective into testable candidates.
- ReviewRead the rationale, code and acceptance results.
- RefineRepair, compare and save the strategies worth keeping.
02 / Backtest
Test the strategy, not a simplified approximation.
Run adjusted daily backtests with fees, slippage, FX conversion, cash and integer positions accounted for outside the strategy code.
VisibleDaily portfolio audit lines
ExplicitFees, slippage and exposure
ComparableMetrics and benchmark context
03 / Portfolios
See how strategies behave together.
Combine saved strategies, inspect their relationship and apply portfolio-level controls without hiding the underlying mix.
- ComposeAdd strategies individually or build the full set.
- InspectReview weights, metrics and correlation structure.
- ControlConfigure optional beta and hedge boundaries.
Built for research
Everything around the strategy matters.
The useful result is not only a return curve. It is a research process you can understand, reproduce and challenge.
Generated does not mean hidden.
Understand the inputs.
Browse adjusted histories, instrument metadata, provider mappings and FX conversion from the same workspace.
Read beyond performance.
Compare drawdown, risk-adjusted metrics, exposure, correlations and benchmark behavior before a strategy joins a portfolio.
Local workspace
Research belongs close to the researcher.
OryxQuant keeps the application workspace on your Windows computer. AI Research sends its selected inputs directly to the LLM provider you configure; the company website does not receive your strategy research.
Read the privacy details ↗Explore OryxQuant
See the complete research workflow.
Move through real application views for AI Research, strategies, portfolios, market data, configuration and backtesting.