kairos
Experimental trading bot for Kraken, Alpaca paper and OKX with Jev-assisted strategies and code-enforced sizing and risk limits.
Overview
Kairos is an experimental trading bot for Kraken, Alpaca hosted paper trading and isolated OKX U.S. demo or live spot accounts. Some strategies are assisted by Jev model assessments, while others, such as Bollinger scalping, DCA, TWAP and rebalancing, need no model calls. A browser dashboard shows live prices, model assessments, orders, fills and portfolio equity with D3 candlestick charts.
Code enforces sizing and execution limits, including starting capital, order and exposure caps, daily loss limits and reinvestment; the README stresses that Jev does not control those safeguards. Settings, order intents, fills and accounting persist in SQLite. The README recommends starting in dry-run with real Kraken data and no orders, and states clearly that live spot execution is implemented but not verified with real orders, that model confidence and simulated returns do not establish profitability, and that full-allocation trading can lose the entire allocation. It is licensed AGPL-3.0.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Should the strategy buy, sell or hold this market now?(inferred) | buy · sell · hold |
| Score | How favourable is the current market assessment?(inferred) | — |
How it works
- Choose market and strategy in settings
- In dry-run, fetch real market data without placing orders
- Model-assisted strategies request Jev assessments
- Code applies sizing, exposure and loss limits
- Orders, fills and equity are recorded and displayed
Strengths
- Risk controls enforced in code
- Dry-run with real data
- Non-model strategies available
- Persistent accounting in SQLite
Caveats
- Live execution not verified with real orders
- No evidence of profitability
- Trading can lose the entire allocation
Getting started
Follow the Quick start and 'Your first dry-run' sections in the README.At a glance
- Type
- Project
- Status
- prototype
- Language
- Python
- Runtime
- bot service with browser dashboard
- Has code
- yes
- Has tests
- yes
- License
- AGPL-3.0
Use cases and integrations
How curated lists describe it
An experimental Python trading bot for Kraken and Alpaca combining Jev-assisted strategy decisions with deterministic risk controls.
logicrw/awesome-jev-projects
Frequently asked questions
Does Jev control risk limits?
No, the README says code enforces sizing and execution limits independently of the model.
Is live trading safe?
Live execution is implemented but unverified; start with dry-run.
Which exchanges are supported?
Kraken, Alpaca hosted paper and OKX U.S. spot (demo or live).
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