Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

jev-bot

Paper-trading experiment where Jev turns a market state into BUY, SELL, HOLD or AVOID, gated by a risk check.

ProjectprototypeCustom license
View on GitHub ↗

Overview

jev-bot is a small open experiment that gives Jev a stream of market states for stocks, crypto and meme assets and asks one question over and over: what is the right action here. Jev returns BUY, SELL, HOLD or AVOID with a calibrated probability in about a tenth of a second, and a risk gate decides whether that decision may reach execution, which is paper trading by default.

The README labels everything by source and mode. Data is simulated by an offline generator by default, with live feeds pluggable behind the same shape. Decisions come from either a transparent local offline engine (the default) or the real Jev model with a key, and every decision states which made it. Execution is paper only, with no wallet, keys or live orders and no live flag. Performance is simulated paper P&L. It explicitly makes no claim that Jev predicts markets and says the developer, not the model, is responsible for acting. It runs on Python 3.10+ with no dependencies for the core and has a custom licence.

What the decision model decides

TypeQuestionAnswers
ChoiceWhat is the right action for this market state?BUY · SELL · HOLD · AVOID

How it works

  1. Generate or ingest a market state
  2. Offline engine or Jev returns an action with probability
  3. Risk gate decides whether the action may execute
  4. Execute on paper and record simulated P&L

Strengths

  • Clear labelling of simulated versus real components
  • No live trading possible by design
  • Offline engine allows use without a key

Caveats

  • Simulated data and P&L by default
  • No evidence of predictive value
  • Custom licence

Getting started

`git clone https://github.com/bl888m/jev-bot && cd jev-bot`, then `python -m jev_bot decisions`.

At a glance

Type
Project
Status
prototype
Language
Python
Runtime
CLI
Has code
yes
License
Custom license

Use cases and integrations

How curated lists describe it

  • JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default

    logicrw/awesome-jev-projects

  • JEV-powered market decision bot for stocks, crypto and memes. State in, BUY/SELL/HOLD/AVOID out, paper by default.

    hellogumbo/awesome-jev

  • Market decision bot for stocks, crypto and memes: state in, buy, sell, hold or avoid out, paper trading by default.

    MrJev/awesome-jev

Frequently asked questions

Does jev-bot trade real money?

No. Execution is paper only and there is no live flag.

What does Jev decide?

BUY, SELL, HOLD or AVOID for each market state.

Can I run it without a key?

Yes, the default decision engine is a local offline one.

Related projects

  • jev-A-share-trader

    Local China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.

    ProjectbetaPython, TypeScript
  • jev-trading

    Local stock decision service that sends market data and news to Jev or a local model and returns a policy-checked buy/sell/hold.

    ProjectbetaTypeScript
  • ml-quant-trading

    PyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.

    ProjectbetaPython
  • QuantStudio

    Chinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.

    ProjectbetaTypeScript
  • traderai

    Self-hosted trading analysis platform pairing Claude briefings with Jev probabilities for signals like thesis-breaking headlines.

    Servicebeta
  • Jev-Trades★ 51

    Next.js crypto dashboard where Jev judges each tick across timeframes and drives a SQLite paper-trading portfolio with automatic TP/SL.

    ServiceprototypeTypeScript