What it is
A Python tool for crypto traders and analysts that screens top coins by market cap using quantitative signals from CoinGecko and Bybit, and classifies news sentiment/catalyst/confirmation via Jev. It prints a table for human reading, not a trading bot.
How it uses Jev
Jev classifies each news item on three questions: sentiment (bullish/bearish), catalyst type, and confirmed-vs-rumor. In scalp.py, Jev acts as a veto: if a recent high-confidence bearish/regulatory news item exists for a symbol, the candidate is suppressed. Results are used to tag or filter candidates in the output table.
Primitives:choicescore
Technique worth stealing
Speculative fan-out: one Jev request per news item covers three questions at once.
Try it
python3 scout.py --top 30 --news (requires a Jev API key)
Evidence
Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.
- Jev-centricunclear0.58
- Shows a System One patternunclear0.52
- Handles uncertaintyno0.07
- Measuredno0.06
- Runnableyes0.85
- Worth recommendingno0.39
- Model replicano0.05
- Problem scopescore on a 0–2 scale0.98
- About Jevyes0.98
Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 21 Sept 2026.