LLM-powered trading agents that turn plain natural language into a five-pillar strategy: Trend, Mean-Reversion, Momentum, Volume, and Risk. Each strategy is hosted, self-evolving, configurable through 30+ tunable parameters, and bit-exact between backtest and live execution. Built for simulated Hyperliquid perpetuals.

轻量级 A 股量化交易执行框架，基于 miniQMT/xtquant，策略插件化，开箱即用

A Rust library for trading on crypto exchanges. Super simple to use. Unified API for different exchanges.

Can a machine learning model beat buy-and-hold on Indonesian stocks? This project builds, tests, and rigorously evaluates a trading strategy powered by XGBoost — one of the most battle-tested ML algorithms in quantitative finance. Tested on Indonesian Stocks

Multi-agent LLM trading framework: hard-discipline (code) + soft-judgment (LLM) hybrid. Best risk-adjusted performance on NVDA 6-month benchmark — +43.9% / -3.2% MDD, beating RSI, Momentum, Buy & Hold, and single-agent LLM. Raw returns top all baselines once the position cap is lifted. Adapted from TauricResearch/TradingAgents, built on LangGraph.

Blankly-Finance-Plugin: Advanced RSI-Trading-Strategy and Machine-Learning tools. Features a Technical-Analysis-API for Crypto-Asset-Management.

Systematic quantitative trading strategy research — backtesting, ML, and funding-rate arbitrage

Black-Scholes pricing and Greeks, variance-reduced Monte Carlo for exotics, and implied-volatility surface construction. A tested, pip-installable Python options-analytics library.

🔴 回测照妖镜 · 一个揪出"让回测虚高、实盘亏钱"陷阱的 Claude Code skill：未来函数/前视偏差、过拟合/数据窥探、成交真实性/成本，输出一张回测体检报告。A Claude Code skill that audits quant backtests for look-ahead bias, overfitting & unrealistic execution.

Avellaneda-Stoikov market-making simulator with inventory control, adverse-selection (markout) diagnostics, and a tabular Q-learning quoting agent.