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.

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

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

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

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