Genetic algorithm breeds and walk-forward tests trading strategies from 484 factors.
484+ factors · Genetic evolution · Walk-forward validated · No API keys needed
⬆️ Real evolution run: 9 crypto assets × 600 generations. Fitness climbs from random (-0.95) to optimized (37.5) — 33% annual return, 6.06 Sharpe, 5.6% max drawdown. (backtest result, not live trading)
Quick Start · Why StratEvo? · How It Works · MCP Server · Discord
pip install stratevo
stratevo evolve --quick # See results in ~2 minutes
stratevo evolve --market crypto # Full evolution (deeper search)No API keys. No exchange accounts. No config files. From install to first evolved strategy in under 2 minutes.
What does it look like? (click to expand)
$ stratevo evolve --quick
⚡ Quick mode — small dataset, fast iterations
Results in ~2 minutes. Use without --quick for full evolution.
============================================================
StratEvo Auto Evolution Engine
============================================================
[factors] loaded 480 dynamic factors
Population: 15 | Elite: 3 | Mutation rate: 0.5
------------------------------------------------------------
Gen 0 | fitness= -1.00 | return= 0.0% | sharpe=-0.74 | trades= 0 | 28s
Gen 5 | fitness= 1.23 | return= 12.4% | sharpe= 0.85 | trades= 14 | 25s
Gen 10 | fitness= 3.60 | return= 18.7% | sharpe= 1.40 | trades= 23 | 27s
═══════════════════════════════════════════
🏆 Best Strategy Found
═══════════════════════════════════════════
Generation: 10
Fitness: 3.60
Annual Return: 18.7%
Sharpe Ratio: 1.40
Max Drawdown: 12.3%
Walk-Forward OOS Results:
Window 0: +6.4% (6 trades) ✅
Window 1: -2.1% (17 trades) ❌
Window 2: +17.2% (14 trades) ✅
Profitable: 2/3 windows
Top Factors:
crypto_bollinger_fast 0.0226 ████
momentum_3d 0.0187 ███
previous_low_test 0.0252 █████
👉 Ready for more? Run full evolution:
stratevo evolve --market crypto
Other tools: Write a strategy → Code → Backtest → Tweak → Repeat
StratEvo: Define the search space → GA evolves strategies → Walk-forward filters survivors
Most quant tools expect you to write the strategy. StratEvo skips that — a genetic algorithm breeds strategies from 484 factors, then walk-forward tests them on unseen data. You get strategies that survived out-of-sample, not just curve-fitted backtests.
| StratEvo | Freqtrade | FinRL / Qlib | |
|---|---|---|---|
| Strategy creation | GA evolves 484-dim DNA | You write rules | DRL trains agent |
| Continuous evolution | ✅ Strategies keep evolving | ❌ Strategy fixed | ❌ Training offline |
| Walk-forward validation | ✅ Multi-window + Monte Carlo | ❌ Plugin needed | |
| Trailing stop | ✅ Evolvable (activation + trail %) | ✅ Manual config | ❌ |
| Position sizing | ✅ Signal-strength weighted | ❌ | |
| Market regime adaptation | ✅ Auto-reduce in bear market | ❌ | ❌ |
| Portfolio correlation guard | ✅ Rejects correlated picks | ❌ | |
| Zero API keys to start | ✅ | ❌ Needs exchange keys | ❌ Needs data setup |
| Markets | Crypto + A-shares + US | Crypto only | A-shares (Qlib) |
| MCP server for AI agents | ✅ | ❌ | ❌ |
| Community & ecosystem | 🆕 Small, early-stage | ✅ Large, mature | ✅ Active (Qlib) |
| Documentation | ✅ Comprehensive | ✅ Extensive | |
| Live trading maturity | ✅ Production-tested |
Seed population (random factor weights)
│
▼
┌─────────────┐
│ Backtest │ Walk-forward: multi-window OOS validation
│ each DNA │ Slippage modeled, position caps, real fees
└──────┬──────┘
│
▼
Select top performers (Sharpe × Return / MaxDrawdown)
│
▼
┌─────────────────────────────────────────┐
│ Cross-sectional neutralization (P0-2) │
│ Correlation-aware selection (P0-1) │
│ Factor diversity bonus (P0-3) │
│ Turnover cost penalty (P0-4) │
└──────┬──────────────────────────────────┘
│
▼
Mutate + Crossover → next generation
│
▼
Repeat
System architecture: data ingestion → factor computation → genetic evolution → walk-forward validation
Every DNA is a weight vector across 484 factors plus advanced risk/position parameters — all evolvable:
| Parameter | What it controls |
|---|---|
hold_days |
Hold period per trade (2–60 days — day trades to swing trades) |
capital_utilization |
Fraction of capital deployed (0.3–1.0) |
position_sizing_power |
Signal strength → allocation weight (0=equal, 2=quadratic) |
trailing_stop |
Lock in profits: trail N% below peak price |
trend_exit_enabled |
Exit on MA crossover — cut losses before stop-loss |
market_regime_sensitivity |
Auto-reduce exposure in bear markets |
profit_target_scaling |
Scale take-profit by signal confidence |
time_decay_exit |
Tighten stop-loss as hold period extends |
scale_in_tranches |
Split entry into 1-3 tranches |
sector_max_pct |
Cap sector concentration (diversification) |
kelly_fraction |
Kelly criterion position sizing based on recent win rate |
The GA tries combinations you wouldn't think of. Anti-overfitting is built in: Arena mode runs multiple strategies simultaneously and penalizes crowded signals.
stratevo evolve --market crypto --generations 50
stratevo evolve --pareto --market crypto # Multi-objective (NSGA-III)
stratevo evolve --logic-guided # Semantically guided mutations📊 484 Factors — 284 general + 200 crypto-native (click to expand)
All normalized to [0, 1]:
| Category | Count | Examples |
|---|---|---|
| Crypto-Native | 200 | Funding rate, session effects, whale detection, liquidation cascade |
| Momentum | 14 | ROC, acceleration, trend strength |
| Volume & Flow | 13 | OBV, smart money, Wyckoff VSA |
| Volatility | 13 | ATR, Bollinger squeeze, vol-of-vol |
| Mean Reversion | 12 | Z-score, Keltner channel position |
| Trend Following | 14 | ADX, EMA golden cross, MA fan |
| Qlib Alpha158 | 11 | KMID, KSFT, CNTD (Microsoft Qlib compatible) |
| Risk Warning | 11 | Consecutive losses, death cross, gap-down |
| Quality Filter | 11 | Earnings momentum, relative strength |
| Price Structure | 10 | Candlestick patterns, support/resistance |
| Sentiment | 2 | EN/ZH keyword sentiment + momentum |
| DRL Signal (experimental) | 2 | Q-learning buy probability + state value |
Weights are determined by the evolution engine — no manual tuning.
StratEvo is designed for extensibility. Every component uses a base class + registry + auto-discovery pattern:
stratevo/
├── factors/ # BaseFactor → add trading factors
│ └── builtin/ # 15 built-in factors (RSI, MACD, ATR, ...)
├── fitness/ # BaseFitness → customize "what's a good strategy"
│ └── builtin/ # 6 built-in (Sharpe, Calmar, Sortino, Composite, ...)
├── datasources/ # BaseDataSource → add data providers
├── exchanges/ # ExchangeAdapter → add exchange connectors
└── cli/commands/
└── scaffold.py # Generate boilerplate for any component
Add a factor in 3 minutes:
stratevo scaffold factor --name my_factor --category momentum
# Edit stratevo/factor_registry/builtin/my_factor.py → implement compute()
# Edit tests/test_my_factor.py → verify it works
# PR it!See CONTRIBUTING.md for the full guide.
StratEvo doesn't just backtest — it tries to break your strategy:
- Arena Mode — Multiple strategies compete in the same simulated market. Crowded signals get penalized.
- Monte Carlo — 1,000 iterations, p-value < 0.05
- Walk-Forward — Multi-window OOS validation with bootstrap confidence intervals
- Cross-Sectional Neutralization — Z-score normalize scores to filter market-wide noise
- Correlation Guard — Rejects highly correlated stock picks (>0.85 Pearson)
- Factor Diversity — HHI-based bonus rewards diversified factor usage, penalizes concentration
- Bias Detection — Look-ahead, snooping, survivorship checks
- Factor Orthogonality — Auto-removes redundant factors
- Turnover Penalty — Excessive trading gets penalized in fitness (modeled as real cost)
These are actual numbers from our running evolution engines — not cherry-picked backtests.
A-Share Elite (428 stocks, 30-DNA population):
| Generation | Fitness | CAGR | Sharpe | Max Drawdown | Win Rate | Trades |
|---|---|---|---|---|---|---|
| Gen 0 | 4.88 | 16.5% | 0.64 | 16.3% | — | — |
| Gen 4 | 18.66 | 50.1% | 0.82 | 27.9% | 32.3% | 414 |
| Gen 6 🏆 | 61.33 | 58.2% | 1.19 | 36.4% | 43.9% | 430 |
Walk-forward out-of-sample (Gen 6 — all 3 windows profitable):
- Window 0: +13.4% annual (worst)
- Window 1: +200.0% annual (best)
- Window 2: +16.4% annual
Crypto (17 assets, 30-DNA population):
| Generation | Fitness | CAGR | Sharpe | Max Drawdown | Win Rate |
|---|---|---|---|---|---|
| Gen 0 | 8.37 | 26.7% | 0.65 | 18.5% | — |
| Gen 19 🏆 | 31.67 | 54.8% | 1.93 | 14.3% | 51.0% |
Expose StratEvo as tools for Claude, Cursor, VS Code, or any MCP client:
{
"mcpServers": {
"stratevo": {
"command": "stratevo",
"args": ["mcp", "serve"]
}
}
}10 tools: get_quote, get_history, list_exchanges, run_backtest, analyze_portfolio, get_indicators, screen_stocks, get_sentiment, compare_strategies, get_funding_rates.
| Command | What it does |
|---|---|
stratevo demo |
See all features in action |
stratevo quote AAPL |
Real-time US stock quote |
stratevo quote BTC/USDT |
Crypto quote via ccxt |
stratevo evolve --market crypto |
Run genetic evolution |
stratevo evolve --pareto |
Multi-objective Pareto evolution |
stratevo backtest -t AAPL |
Backtest a strategy |
stratevo check-backtest |
Verify backtest integrity |
stratevo analyze TSLA |
Technical analysis |
stratevo copilot |
AI financial assistant |
stratevo mcp serve |
Start MCP server |
stratevo paper |
Paper trading mode |
python -m stratevo.viz.evolution_tree <log> |
ASCII evolution timeline |
python -m stratevo.viz.parse_evolution_log <log> |
Parse evolution log → JSON |
70+ commands total — run stratevo --help for the full list.
| Market | Source | API Key? |
|---|---|---|
| Crypto | ccxt (100+ exchanges) | No |
| US Stocks | Yahoo Finance | No |
| A-Shares | AKShare + BaoStock | No |
| Sentiment | CryptoCompare + AKShare | No |
The web dashboard (dashboard/) provides 7 pages: market overview, backtesting, strategy comparison, evolution monitoring, portfolio management, stock screening, and individual stock analysis with technical indicators.
cd dashboard && npm install && npm run devNote: Dashboard screenshots are from development builds and may show placeholder data. Run the dashboard locally to see live results from your own evolution runs.
Watch: How StratEvo's Evolution Engine Works (2 min)
- 484-factor evolution engine
- Walk-forward + Monte Carlo + Arena mode
- Bias detection suite
- MCP server for AI agents
- Multi-objective Pareto evolution (NSGA-III)
- Market Logic Layer (semantically guided mutations)
- Paper trading infrastructure
- Evolution visualization (CLI ASCII tree + interactive HTML dashboard)
- Advanced position sizing (signal-strength weighted)
- Trailing stop loss (evolvable activation + trail %)
- Market regime adaptation (auto-reduce in bear markets)
- Cross-sectional score neutralization
- Portfolio correlation guard
- Factor diversity optimization (HHI-based)
- Swing trading support (hold periods up to 60 days, dynamic trend exits)
- Plugin architecture (Factor/Fitness/DataSource registries + scaffold CLI)
- DEX execution (Uniswap V3 / Arbitrum)
- Multi-timeframe strategy evolution (1h / 4h / 1d)
- Multi-strategy ensemble (regime-switching)
- Short selling for crypto
- Factor decay detection (rolling IC monitoring)
- Foundation model for price sequences
- Web dashboard with live P&L tracking
- QuantConnect-style cloud execution (SaaS)
- Mobile alerts via Telegram/Discord
- Community strategy marketplace
This project is for educational and research purposes only. Not financial advice. Past performance does not guarantee future results. Always paper trade first.
| Project | What it does |
|---|---|
| ClawGuard | AI Agent Immune System — 480+ threat patterns, zero dependencies |
| AgentProbe | Playwright for AI Agents — test, record, replay agent behaviors |
StratEvo is built for contributors. The plugin architecture makes it easy to add new components without touching core code.
# 1. Generate boilerplate
stratevo scaffold factor --name bollinger_squeeze --category volatility
# 2. Implement compute() in the generated file
# 3. Run tests
pytest tests/test_bollinger_squeeze.py -v
# 4. Submit a PR ✅That's it — one file, one function, one PR. The scaffold command generates both the factor and its test template.
| Component | Difficulty | Command |
|---|---|---|
| Factors | 🟢 Easy | stratevo scaffold factor --name xxx --category momentum |
| Fitness functions | 🟡 Medium | stratevo scaffold fitness --name xxx |
| Data sources | 🟡 Medium | stratevo scaffold datasource --name xxx |
| Strategy DNA | 🟠 Advanced | Share evolved YAML configs |
| Bug fixes | 🟢-🟡 | Check good first issue |
git clone https://github.com/NeuZhou/stratevo.git
cd stratevo && pip install -e ".[dev]" && pytestCONTRIBUTING.md · Discord · Report Bug · Request Feature
If this is useful, a ⭐ helps others find it.
Previous versions reported inflated backtest returns caused by look-ahead bias and short validation windows. This has been fixed — scoring uses previous-period data, position sizes are capped, slippage is modeled, and walk-forward validation uses year-long OOS windows with OOS return gates (strategies that lose money out-of-sample get zero or negative fitness regardless of in-sample performance). Use stratevo check-backtest to verify results.