QuantStudio
Chinese open-source research and trading workbench whose JEV monitor watches futures contracts and judges entries and exits.
Overview
QuantStudio, from PandaAI's QuantSkills community, is a local workbench for quant research, daily office work and trade execution. It can check a backtest, organise Excel files, make reports, and connect to a futures simulation contest account. The README is in Chinese, with an English version available, and includes long install prompts meant to be handed to a coding agent.
The Trade section has three entry points sharing a connected contest account: JEV monitoring, an AI trader and AI assistance. In JEV monitoring you write a strategy and its entry, exit and wait conditions, and TypeSafe Jev continuously judges them against candlesticks, quotes, positions and constraints, across multiple contracts. You choose per-order confirmation or authorise automatic orders at start. JEV needs its own TypeSafe key. Pausing stops new orders but does not cancel submitted ones or close positions, and the contest API has rate limits.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Given K-lines, quotes, position and constraints, should the plan enter, exit or wait?(inferred) | enter · exit · wait |
How it works
- Configure models, a TypeSafe key and PandaData market data
- Connect the futures contest account
- Describe strategy and entry/exit/wait conditions
- Jev monitors contracts and judges conditions continuously
- Confirm each order or allow auto-ordering
Strengths
- Continuous monitoring with a cheap decision model
- Per-order confirmation option keeps a human in the loop
- Supports multiple contracts
Caveats
- Targets simulated futures contests; pausing does not cancel or close positions
- JEV futures CLI runs on Windows and macOS only
- Dual GPL-3.0-or-later / commercial licence
Getting started
git clone the repo, corepack enable, corepack pnpm install --frozen-lockfile, then corepack pnpm run web.At a glance
- Type
- Project
- Status
- beta
- Language
- TypeScript
- Runtime
- Local web app (Node)
- Has code
- yes
- Has tests
- yes
- License
- GPL-3.0-or-later
Use cases and integrations
How curated lists describe it
Local research and trading workbench with a Jev module that watches positions and grades trade plans. Chinese. GPL-3.0.
MrJev/awesome-jev
Frequently asked questions
What does JEV monitoring decide?
Whether your written entry, exit or wait conditions are met given market data, positions and constraints.
Does it trade automatically?
Only if you authorise automatic orders at start; otherwise each order is confirmed.
Is it in English?
The main README is Chinese; an English README is linked.
Related projects
Self-hosted trading analysis platform pairing Claude briefings with Jev probabilities for signals like thesis-breaking headlines.
ServicebetaStock terminal that gathers live evidence via Valyu and asks Jev for the probability a stock trades higher in 30 days.
ProjectprototypeTypeScriptJev demo that reads live yfinance profiles and headlines into ranked, grounded and routed trade ideas, showing every request.
AppprototypePython- QuantDinger★ 12,754
Self-hosted open-source AI trading OS with research, backtesting and paper/live execution, advertising Jev-powered pre-trade decisions.
LibraryproductionPython Watches X for updates relevant to your YAML profile, has Jev classify and score each post, and alerts in Slack.
ProjectbetaTypeScriptWorking paper placing a text judge beside a live trading system as a read-only signal, comparing Jev and Claude as blind headline judges.
Paperresearch