traderai
Self-hosted AI trading intelligence platform - scoring engine, two-model AI analyst (Claude + TypeSafe Jev), risk engine, discipline guardian, backtester, React dashboard
How it uses Jev
Macro Themes : the themes you track, scored against today's real headlines with calibrated Jev probabilities. A Reuters Hormuz headline lights up Iran Hormuz at 96% while quiet themes sit at 3%.
Highlights
- 180-point entry scoring over 14 factors (RSI, MACD, Bollinger %, FCF yield, insider buying, macro-narrative alignment…) with hard disqualifiers and a backtested falling-knife guard
- 150-point spec scorer for pre-profit small caps - cash runway, dilution, customer concentration instead of FCF
- Lead indicators that move before price: SEC Form 4 insider signals, options flow + gamma walls, supply-chain upstream reads
- Universe scanner ( 350 stocks, one click from the UI), earnings calendar with disqualifier warnings, dividend calendar, monthly recap, market breadth
- 730-day backtester with bootstrap-CI guard validation and 60-day forward logs for every experimental signal
- SQLite signal store - every day's computed signals are logged, building your own research dataset for free
- Languages
- Python 79% · JavaScript 21% · CSS 1% · PowerShell 1%
- License
- MIT
- Last activity
- Sep 2026
- Added
- 2026-09-23
- Stars at snapshot
- 4
- Status
- Community listing
Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.