NeuZhou

NeuZhou / finclaw

Public

AI-native quantitative finance engine. Quotes, backtesting, paper trading, strategy evolution, and MCP server.

ai ai-agents ai-trading algorithmic-trading backtesting
15
2
89% credibility
Found Mar 22, 2026 at 15 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

FinClaw is an open-source quantitative finance platform that uses genetic algorithms to evolve trading strategies across multiple markets including US stocks, crypto, and Chinese A-shares, with a production dashboard for analysis and backtesting.

How It Works

1
🔍 Discover FinClaw

You find this helpful tool online that automatically improves trading ideas using smart evolution.

2
📦 Install easily

With one simple command, you add it to your computer and everything is ready to go.

3
🚀 Launch your dashboard

Open the colorful web screen showing live prices, charts, and market scanners from around the world.

4
📊 Explore markets

Browse stocks, crypto, and global indices, compare tickers, and screen for opportunities.

5
🔄 Evolve strategies

Hit play to let the system automatically test and improve hundreds of trading ideas over generations.

🏆 Review top performers

See the best evolved strategies with their returns, risks, and backtest results, ready for you to use.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 15 to 15 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is finclaw?

FinClaw is a Python-based AI-native quantitative finance engine for fetching quotes, backtesting strategies, paper trading, and evolving them via genetic algorithms across 41 technical, fundamental, and quality factors—no human tweaks needed. It pulls data from Yahoo Finance, ccxt, and AKShare for US stocks, crypto, and Chinese A-shares, with a React dashboard showing real-time prices, screeners, TradingView charts, and an AI chatbot. CLI starts instantly: pip install finclaw-ai; finclaw demo or finclaw quote AAPL.

Why is it gaining traction?

Self-evolving strategies run 24/7 with walk-forward validation and Monte Carlo tests to fight overfitting, plus a multi-agent debate arena for consensus signals. The MCP server exposes 10 tools like run_backtest and screen_stocks for AI agents, making it a plug-and-play backend for ai native development github projects. Zero API keys and PyPI packaging lower barriers versus setup-heavy alternatives like Freqtrade or Backtrader.

Who should use this?

Quant devs prototyping strategy evolution on global markets; AI builders wiring finance tools into Claude or Cursor via MCP server; finance researchers needing quick backtesting, paper trading, and dashboards without data plumbing.

Verdict

Solid for experiments—15 stars reflect early stage, but 0.9% credibility score underrates the tested dashboard and PyPI ease. Fork it for personal ai-native github backtesting engine if production polish isn't urgent.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.