English | 中文 | 한국어 | 日本語

pip install finclaw-ai
finclaw demo                      # See it in action
finclaw evolve --market crypto    # Start evolving strategies

No API keys. No exchange accounts. No config files.

$ finclaw demo

=== Strategy Evolution ===

Population: 30  |  484 factors  |  Walk-forward validated

  Gen    Return    Fitness   Sharpe
  ---    ------    -------   ------
    1      3.2%       12.1     0.4
   25     18.4%       89.2     1.3
   50     31.6%      156.7     1.7
  100     48.5%      245.8     2.2

Top factor weights: RSI 0.34, Momentum 0.25, MACD 0.18, Volume 0.12

=== Backtest ===

Strategy:  +75.7%  (+32.5%/yr)    Buy&Hold:  +67.7%
Sharpe:    1.85                   MaxDD:     -8.3%

Most quant tools expect you to write the strategy. FinClaw evolves them instead.

A genetic algorithm breeds a population of strategies across 484 factor dimensions — momentum, volume, volatility, crypto-native signals, sentiment — then walk-forward tests the survivors. You get strategies that work on unseen data, not just historical curves.

   Seed population (random factor weights)
         │
         ▼
   ┌─────────────┐
   │  Backtest    │  Walk-forward: 70% train / 30% test
   │  each DNA    │  Slippage modeled, position caps
   └──────┬──────┘
          │
          ▼
   Select top performers (Sharpe × Return / MaxDrawdown)
          │
          ▼
   Mutate + Crossover → next generation
          │
          ▼
        Repeat

Every DNA is a weight vector across 484 factors. The GA explores combinations no human would try. Anti-overfitting is built in: Arena mode runs multiple strategies simultaneously and penalizes crowded signals.

finclaw evolve --market crypto --generations 50
finclaw evolve --pareto --market crypto     # Multi-objective (NSGA-III)
finclaw evolve --logic-guided               # Semantically guided mutations

FinClaw doesn't just backtest. It stress-tests:

• 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 — 70/30 train/test split with bootstrap confidence intervals
• Bias Detection — Look-ahead, snooping, survivorship checks
• Factor Orthogonality — Auto-removes redundant factors
• Turnover Penalty — Excessive trading gets penalized in fitness

Expose FinClaw as tools for Claude, Cursor, VS Code, or any MCP client:

{
  "mcpServers": {
    "finclaw": {
      "command": "finclaw",
      "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.

70+ commands total — run finclaw --help for the full list.

Watch: How FinClaw'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)
• DEX execution (Uniswap V3 / Arbitrum)
• Multi-timeframe strategy evolution (1h / 4h / 1d)
• 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.

Honest disclosure: Previous versions reported inflated backtest returns caused by look-ahead bias. This has been fixed — scoring now uses previous-period data, position sizes are capped, and slippage is modeled. Use finclaw check-backtest to verify results.

We welcome contributions! Here's how to get started:

1. Pick an issue — look for good first issue labels
2. Fork & clone

   git clone https://github.com/NeuZhou/finclaw.git
   cd finclaw && pip install -e ".[dev]" && pytest

3. Submit a PR — we review within 48 hours

CONTRIBUTING.md · Discord · Report Bug · Request Feature

AGPL-3.0