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.
Overview
jev-A-share-trader is a Chinese-language technical analysis workbench for China A-shares, with an English option. It fetches market data through AKShare (default, no key) or Tushare Pro, computes indicators and pattern evidence across eight dimensions (trend, momentum, volume-price, volatility, price structure, candlestick patterns, multi-timeframe and relative strength), and asks Jev to assess each dimension before combining them into one Buy, Hold or Sell judgment with an automatically chosen horizon of 2-5 or 5-20 trading days.
Each report shows supporting, opposing and background evidence linked to specific candles, and analysis uses only completed trading days. It supports single-stock analysis, watchlists and batch scans of up to 50 stocks with pause, resume and retry, through a web UI and a CLI with JSON, CSV and HTML export. It never executes orders. Without a Jev key it still shows charts and facts but marks the judgment as not formed rather than substituting a default. It is MIT licensed.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Overall assessment for this stock | Buy · Hold · Sell |
| Choice | Which horizon applies? | 2-5 trading days · 5-20 trading days |
| Yes / no | Does the evidence in this dimension support upward direction or elevated volatility?(inferred) | yes · no |
How it works
- Fetch daily, weekly and monthly data from AKShare or Tushare
- Compute indicators and pattern evidence in eight dimensions
- Jev assesses each dimension
- Combine into Buy/Hold/Sell with horizon and traceable evidence
- Export results; no orders are placed
Strengths
- Evidence for and against is shown, not just a verdict
- No default conclusion when Jev is not configured
- Batch scanning with resume and retry
- Uses only completed periods to avoid look-ahead
Caveats
- Technical analysis only; not investment advice
- Primarily Chinese documentation
- Windows requires WSL
Getting started
`pip install -e .`, build the frontend with npm, then `jev serve` and open http://127.0.0.1:8765; or `jev analyze 000001` from the CLI.At a glance
- Type
- Project
- Status
- beta
- Language
- Python, TypeScript
- Runtime
- local web app and CLI
- Has code
- yes
- License
- MIT
Use cases and integrations
How curated lists describe it
A Jev-powered technical analysis workspace for China A-shares, supporting AKShare/Tushare, market scans, and Buy/Hold/Sell assessments with time horizons and traceable evidence.
logicrw/awesome-jev-projectsLocal A-share technical analysis using Jev Choice and Noul questions to assess direction and volatility across two horizons, with evidence for Buy/Hold/Sell assessments and no order execution.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev decide here?
Assessments of each technical dimension and an overall Buy, Hold or Sell judgment with a horizon.
Does it place trades?
No. It only produces analysis and never executes orders.
Can I use it without a Jev key?
Yes for charts and indicator facts; the judgment is then shown as not formed.
Related projects
Stock terminal that gathers live evidence via Valyu and asks Jev for the probability a stock trades higher in 30 days.
ProjectprototypeTypeScriptExperimental Polymarket bot: a web-search model writes an evidence brief, Jev prices P(YES), and code trades only on a configured edge.
ProjectprototypePythonTerminal agent for Polymarket 5-minute BTC markets that asks Jev up or down and buys once only above 0.90 confidence; dry-run default.
ProjectprototypeTypeScriptPolymarket BTC 5-minute up/down agent: code prices with a volatility model, Jev scores regime and vetoes anomalies; paper by default.
ProjectprototypePythonPaper-only research tool for Polymarket BTC 5-minute Up/Down markets: Jev scores the direction, separate code decides entries.
ProjectresearchTypeScriptExperiment that builds past-only Hong Kong market state and asks Jev for an up, flat or down forecast, with a standalone HTML report.
ProjectresearchPython