beebots
Three paper-trading bots race on OKX perpetual futures with every decision made by Jev and every order passing a plain-code risk layer.
Overview
beebots runs three AI trading bees that race each other on OKX perpetual futures. Every trading decision comes from Jev, and every order goes through a risk layer written in ordinary code. A public live dashboard shows each decision, order, fee and funding payment as it happens. It runs on paper by default, using real prices and simulated money (each bee starts with $333), and only touches an exchange account if you deliberately change settings.
Each bee has a trading style and written rules that go to Jev with every decision; Jev picks among the moves the style allows. A separate coach, run as a Zapier Zap where Jev picks the bee and Claude rewrites its rules, adjusts bees whose rules are wrong. Jev spending is capped at $2 a day by default, keys are never shared, and setup is a one-click VPS deployment with a time-limited setup page and owner password. The README stresses it is an experiment, not financial advice.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which move should this bee make now, within its style and rules? | — |
| Choice | Which bee needs new rules? (coach) | — |
How it works
- Fetch live market data
- Send state plus the bee's rules to Jev
- Jev picks a move from allowed options
- Risk layer in code checks and places the paper order
- Dashboard records decisions, orders, fees and funding
Strengths
- Paper trading by default
- Deterministic risk layer
- Daily Jev spend cap
Caveats
- Not financial advice; leveraged crypto can lose everything
- Public dashboard by design
- Promotes a paid VPS setup
Getting started
Deploy via the one-click VPS button, then on the Setup page accept the risk statements, set an owner password and paste your Jev key.At a glance
- Type
- Model
- Status
- prototype
- Runtime
- Docker on a VPS + web dashboard
- Has code
- yes
Use cases and integrations
How curated lists describe it
Three AI trading bees on OKX, every decision by Jev. Paper trading by default.
wh000wh000/awesome-jev-liveThree trading bots race on OKX perpetual futures with every decision typed and a risk layer in plain code; paper trading is the default. Not financial advice.
MrJev/awesome-jev
Frequently asked questions
Does it trade real money?
Not by default; it paper-trades unless you change settings yourself.
What does Jev decide?
Each bee's next move within its style and rules.
How is Jev cost limited?
A default cap of $2 per day.
Related projects
Local China A-share technical analysis workbench where Jev assesses eight indicator dimensions and returns Buy, Hold or Sell with evidence.
ProjectbetaPython, TypeScriptLocal stock decision service that sends market data and news to Jev or a local model and returns a policy-checked buy/sell/hold.
ProjectbetaTypeScriptPyTorch factor-research stack with 213 factors and cost-aware backtests, plus a preview typed portfolio-decision adapter.
ProjectbetaPythonChinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.
ProjectbetaTypeScriptSelf-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