Start with a free evidence check. Upgrade to Pro when you need to attack overfitting on full history — on your Mac or a 24/7 Docker server.
No credit card for Free · Cancel paid plans anytime · Your data stays local
Free
Discover a signal
Get the first evidence
Pro
Try to break it
Attack overfit before deployment
01 · Discover
Discover promising signals on your own data before paying
02 · Prove
Prove robustness, optimize at scale, and train trading models
One license works with the local Mac app or Docker Server Edition · your research stays on hardware you control
Bring RSI, order-flow data, calendar fields, or indicators with any name. RLXBT ranks what carries signal, checks whether a feature adds nonlinear value out of sample, and then demands evidence from a strategy that can actually trade it.
Neural evidence is treated as a lead, not proof. Promotion requires stable folds and executable strategy evidence.
Quality, information coefficient, stability, and response profiles expose weak or leaky inputs early.
A challenger neural model must beat the price-only baseline across expanding out-of-sample folds and seeds.
Generated strategy probes check whether the discovered pattern survives rules, costs, and real execution logic.
Compare by outcome
The agent and Feature Lab stay. Your research depth and standard of proof increase.
| Research capability | DiscoverFree | Prove & trainPro |
|---|---|---|
| MCP agent + full Feature Lab | Included | Included |
| Bars per backtest | 10K | Unlimited |
| Saved visual research workspace | — | Included |
| Walk-Forward + Monte Carlo | — | Included |
| Sensitivity + portfolio + intrabar | — | Included |
| DQN reinforcement learning | — | Included |
| Mac or Docker Server | Included | Included |
| Active devices | 1 | 3 |