StratEvo

io.github.NeuZhou由 GitHub 帳號 NeuZhou 發布v6.0.3更新於 Nov 3, 2026

Quantitative trading: quotes, backtesting, screening, and genetic algorithm strategy evolution.

已驗證STDIO僅桌面金融資料與分析

概覽

AI 產生的概覽

StratEvo 是本地量化交易引擎，讓助理取得行情、回測、篩選並以遺傳演算法演化交易策略。

可以做什麼
  • 執行量化交易流程：取得報價、回測與市場篩選
  • 以遺傳演算法在 484 個以上市場因子上演化策略，調整因子權重與風險參數
  • 透過前向滾動檢驗、蒙地卡羅、CPCV 與偏差偵測驗證候選策略
  • 檢視專案公布的即時訊號與模擬交易（paper trading）績效
適用情境
適合想讓助理探索或回測系統化交易想法、篩選市場，或執行遺傳演算法策略演化與穩健性檢驗，而非手寫規則的情境。
執行需求
以本機 stdio 程序執行，從 PyPI 套件 stratevo 安裝，需要 Python 環境。未宣告任何驗證、環境變數或標頭。README 說明完整的演化引擎、模擬交易、訊號產生與實盤交易所連接器屬於付費 Pro 版本，需聯絡作者取得。
安裝前請注意
涉及真實金融市場：README 中的回測數據明確不是實盤交易，早期版本還曾因前視偏差錯誤出現虛高報酬。實盤交易所連接器意味著交易操作與可能的資金支出。Pro 引擎需商業聯絡而非直接安裝，README 另列出電子郵件與 Discord 邀請連結。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 StratEvo，將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Desktop only，透過 STDIO。 STDIO 服務會啟動本機處理程序，因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README


🦀 StratEvo

Stop writing trading strategies. Evolve them.

A genetic algorithm engine that breeds and walk-forward validates trading strategies across 484+ market factors.

[484+ Evolvable Factors] [Markets] [Validation] [Discord]

Live Signals · Paper Trading · How It Works · Results · Robustness · Get Access

📡 Live Signals

Real-time buy/sell signals from evolved strategies. Updated daily. All signals are committed to git history — you can verify every one.

Latest Signals

DateMarketActionAssetEntry PriceDNAStatus
Signals will be posted here as Paper Trading goes live

📁 Full signal history: signals/

📊 Paper Trading Performance

Forward-testing evolved strategies on real market data with simulated execution. No hindsight, no cherry-picking.

Paper Trading active — Crypto V13 live since 2026-04-18.

Current Paper Portfolio

StrategyMarketStart DateDaysReturnSharpeMaxDDTradesStatus
Crypto V13Crypto2026-04-180————🟢 Live

📁 Daily P&L reports: paper-trading/
📈 Equity curves: paper-trading/charts/

Equity Curve (demo — real data accumulating)

[Equity Curve]

Drawdown

[Drawdown]

How It Works

Most quant tools make you write the strategy. StratEvo evolves them instead.

You write the rules        →  StratEvo discovers the rulesYou tune parameters        →  GA tunes parameters  You test on one period     →  Walk-forward tests on multiple windowsYou hope it generalizes    →  Monte Carlo measures if it does
  Random DNA population (484 factor weights + risk parameters)       │       ▼  ┌──────────────────────┐  │  Walk-Forward Test   │  Multi-window out-of-sample validation  │  each DNA candidate  │  Real fees, slippage, position caps  └──────────┬───────────┘             │             ▼  Keep the survivors (fitness = Sharpe × Return / MaxDD)             │             ▼  Mutate + Crossover → next generation             │             ▼  Repeat for N generations

Each DNA is a weight vector across 484+ factors plus risk/position parameters — all evolvable:

ParameterRangeWhat it controls
Factor weights (×484)0.0–1.0Which factors matter and how much
hold_days2–60Day trades through swing trades
trailing_stop%Trail below peak to lock in profits
market_regimesensitivityReduce exposure automatically in bear markets
kelly_fraction0–1Position sizing from recent win rate

Evolution Results

Numbers from our running evolution engines. Updated as generations progress.

🇺🇸 US Stocks V8 (100 S&P 500 stocks — Gen 136)

MetricBest DNA
Annual Return33.5%
Sharpe Ratio1.47
Max Drawdown17.0%
Win Rate55.5%
Profit Factor1.75
Total Trades179

₿ Crypto V13 (17 assets — Gen 53)

MetricBest DNA
Annual Return69.0%
Sharpe Ratio2.27
Max Drawdown13.0%
Win Rate50.0%
Profit Factor1.58
Total Trades174

These are backtests with walk-forward validation, not live trades. That's the whole point of paper trading — proving it works forward, not just backward.

Anti-Overfitting

We learned this the hard way. An early version showed 25,000% returns. Turned out to be a bug — look-ahead bias.

DefenseWhat it does
Walk-ForwardMulti-window OOS validation. Must profit on data it never trained on.
Monte Carlo1,000 shuffled iterations. p-value < 0.05 or it's luck.
CPCVCombinatorial Purged Cross-Validation. Industry standard for a reason.
Arena ModeMultiple strategies compete head-to-head. Crowded signals get penalized.
Bias DetectionLook-ahead, snooping, survivorship — flagged automatically.
Turnover PenaltyExcessive trading is punished. Real transaction costs baked in.

An honest 33% beats a fake 25,000%.

484+ Factors

CategoryCountExamples
Crypto-Native200Funding rate, whale detection, liquidation cascade
Momentum14ROC, acceleration, trend strength
Volume & Flow13OBV, smart money, Wyckoff VSA
Volatility13ATR, Bollinger squeeze, vol-of-vol
Mean Reversion12Z-score, Keltner channel position
Trend Following14ADX, EMA golden cross, MA fan
Qlib Alpha15811Microsoft Qlib compatible factors
+ 5 more categories37Risk, quality, price structure, sentiment, DRL

All factor weights are discovered by evolution. Zero manual tuning.

Strategy Styles

The algorithm converges on recognizable trading styles on its own:

StyleWhat the DNA learned
Value SeekerBuys cheap, holds patient
Momentum RiderChases runners, dumps laggards
Mean ReverterBets on bounce-backs
Flow ReaderFollows the money — volume leads price
Volatility HunterProfits from vol expansion
Crypto Native200 factors built for 24/7 markets

Get Access

StratEvo Pro includes the evolution engine, paper trading, signal generation, and live exchange connectors.

📧 Contact: [email protected]
💬 Discord: discord.gg/kAQD7Cj8

Technical Papers

Check back daily for updated signals and paper trading results.

來源：README.md，提交 345d7c6

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包，因此其工具未知。

版本歷史

1
  1. v6.0.3最新Sep 16, 2026

評分

已滿足適用檢查項的 40%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通25 分

    請保持端點能夠回應 MCP 握手；SourceWeft 每 30 天探測一次。

  • 已宣告認證方式10 分

    請在註冊中心條目中宣告憑證請求標頭，或保持端點能夠回應探測，以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分

    請在儲存庫或註冊中心條目中宣告授權條款。