Jeeva
Modular Hyperliquid perpetuals trading engine whose DecisionMaker asks Jev for a long, short or flat target per market.
Overview
Jeeva is an AI-assisted, mid-frequency trading framework for Hyperliquid perpetual futures, built with a Next.js dashboard, an Express API and a Rust trading engine backed by MongoDB. It was first built to test trading with Jev and has grown into a general engine that can host other algorithms. For each enabled market it samples price, open interest, volume and spread, prunes old samples, and periodically builds a summary of recent conditions.
That summary goes to a pluggable DecisionMaker (Fake, TypeSafe Jev or OpenRouter Jev) that returns a target direction: long, short or flat. If the target differs from the current position, the engine closes or opens accordingly, without pyramiding. New markets and fresh deployments always start in mock mode against a simulated wallet, and real orders require explicitly switching a market to live with wallet credentials configured. If a market's decision cycle fails five times in a row, the engine force-flattens the position. The dashboard tunes frequency and aggressiveness and shows decisions, positions and P&L live.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Given recent market conditions, what should the target direction be? | long · short · flat |
How it works
- Sample market data for enabled perpetuals
- Summarise recent conditions per market
- DecisionMaker (Jev) returns long, short or flat
- Engine adjusts position only if the target changed
- Five consecutive failures force-flatten the position
Strengths
- Mock mode by default; live trading needs explicit opt-in
- Pluggable decision engines for comparison
- Automatic flattening on repeated failures
- CI and MIT licence
Caveats
- No evidence the strategy is profitable; it is a framework
- Trading real funds carries financial risk
- Requires MongoDB, Node and Rust services
At a glance
- Type
- Service
- Status
- prototype
- Language
- Rust, TypeScript
- Runtime
- Rust engine, Express API, Next.js dashboard
- Has code
- yes
- Has tests
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
Mid-frequency trading framework for Hyperliquid perpetuals whose decision makers are typed questions, in a TypeScript API and a Rust engine.
MrJev/awesome-jev
Frequently asked questions
What does Jev decide in Jeeva?
The target direction for each perpetual market: long, short or flat.
Will it trade real money by default?
No. Markets start in mock mode and live trading needs an explicit switch and wallet credentials.
Can I plug in other strategies?
Yes, DecisionMaker is pluggable; Fake, TypeSafe Jev and OpenRouter Jev are included.
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