jevbooks

← All projects

trading-bot-jev

Spykoninho/trading-bot-jev

Crypto trend-following bot using Jev to judge news.

Finance & Trading0.97Runner-up: Scoring & RankingThermostat
Automated README summary

Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A medium-term trend-following crypto trading bot for Bitvavo, with a paper portfolio by default and optional real execution. It asks whether Jev, TypeSafe's System One model, adds value over a pure algorithm.

How it uses Jev

Jev judges each news item with typed questions: affected asset, sentiment, materiality, regulatory risk. The code uses only two effects: a news bias shifting the two EMA thresholds by at most ±0.5%, and a regulatory veto on buys. A separate EVENT_RULES circuit acts immediately on Trump posts.

Primitives:choicescore

Technique worth stealing

Separate the model's role: Jev reads and classifies news, while the algorithm computes trend, sets thresholds, sizes and executes.

Try it

npm install, set TYPESAFE_API_KEY in .env, then npm start; UI at http://localhost:3210.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.13.0
Project signals
jev-1.13.0
Category
jev-1.13.0
Pattern tags
jev-1.13.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectnot found in the excerpt0.37
  • Shows a System One patternunclear0.44
  • Describes handling uncertaintynot found in the excerpt0.08
  • Reports measured numbersnot found in the excerpt0.08
  • Is a runnable toolFound in material0.79
  • Top-10 learning shortlist signalnot found in the excerpt0.30
  • Is a replica of the modelnot found in the excerpt0.05
  • Solves a common problem (0–2)score on a 0–2 scale0.31 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.37Shows a System One pattern0.44Describes handling uncertainty0.08Reports measured numbers0.08Is a runnable tool0.79Top-10 learning shortlist signal0.30Is a replica of the model0.0500.51Solves a common problem (0–2)0.31 / 2012

no-judgment band (0.40–0.60)

Design patterns
Thermostat0.96Flight recorder0.47Traffic light0.31Check-up0.28Funnel0.2700.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 21 Oct 2026.