1 Layer 1 · Aggregation
Signals from four sources: classic, factor, ML, AI hypothesis.
Bring classic strategies, factors, ML models, and AI-assisted hypotheses into an inspectable candidate set. Candidate generation does not establish validity.
AI-Native Quant Research
StratCraft
Move from hypothesis to data, candidates, experiments, reproducible evidence, and the next research decision.
AI guides the workflow. You remain in control.
AI-Native Quant Research · human-controlled
Research evidence · evaluation and transparent baselines
Illustrative interface, not a performance claim500–1000×
workload-specific benchmarks
2000+/sess
reviewed candidates
7
LLM providers
1000+
governed research set
Research Capabilities in Context
Product maturity is measured by evidence and governed decisions, not candidate volume.
0
AI helps frame, build, and explain research
0
Users approve operations and next decisions
0
Community execution, Artifacts, evidence, and lineage
0
Community, hosted inference, and Commercial boundaries
The Research Capability Chain
AI connects research work while the user controls operations and decisions.
2 Layer 2 · Speed
Local C++23 execution, with workload-specific evidence.
Run approved backtests locally and preserve inputs, Artifacts, lineage, and results. Performance claims remain benchmark-specific.
Python
(vectorbt)1×
(vectorbt)1×
Rust
(NautilusTrader)42×
(NautilusTrader)42×
StratCraft
C++23784×
C++23784×
3 Layer 3 · Composition
Transparent evaluation. Governance before promotion.
Compare candidates against appropriate baselines and retain acceptance or rejection evidence. Advanced fusion remains separately admitted.
∞ All local · no lock-in
Windows, macOS, Linux. Local-first research execution.
Community AI Studio supports loginless direct BYOK or a supported local model. Optional hosted inference is a separate, disclosed boundary.
Windows
macOS
Linux
Why Research Continuity Matters
Connected evidence and decisions matter more than generating a larger candidate count.
Conventional Approach
StratCraft Research Workflow
Signal sourcing
Hand-craft 3-5 strategies manually
pages.quantnexus.scaleComparison.row1Quantnexus
Backtest throughput
Disconnected tools and incomplete run context
pages.quantnexus.scaleComparison.row2Quantnexus
Portfolio composition
Pick your best strategy and run it
pages.quantnexus.scaleComparison.row3Quantnexus
Structural approach
Concentration risk. One strategy fails, you fail
pages.quantnexus.scaleComparison.row4Quantnexus
A larger search space creates more opportunities for false discoveries. StratCraft treats evidence, rejection, and research memory as first-class product responsibilities.
The 3-Layer Pipeline
1
Layer 1: Aggregate from Four Sources
Bring together classic strategies (open-source libraries, published systems, TradingView, your own), quant factors, ML models, and LLM-generated hypotheses. One idea becomes a population of candidates, not a single hand-coded strategy.
2
Layer 2: Backtest the Whole Factory
The local C++23 engine runs approved backtests and retains inspectable results. Named data routes and performance evidence are stated per workload.
3
Layer 3: Statistical Composition
Compare surviving candidates with transparent baselines. Community includes equal-weight combination and replay; advanced fusion and decision policies are separately admitted.
Go Deeper
Research Modules, One Connected Workflow
Every module in the 3-layer pipeline. From four-source aggregation through C++23 execution to statistical composition.
Explore →Why C++23 Speed Matters at Scale
Architecture evolution, workload-specific benchmark evidence, and local execution boundaries.
Explore →Start Your Signal Factory
Free tier includes the C++ backtest engine, regime detection, and YFinance + Dukascopy data: everything you need to start building at scale.