Projects

A next-generation algorithm textbook for the AI age. When coding agents can write code, the core skill becomes judgment—how to judge problem types, solution correctness, complexity, and modeling direction.

Customer classification on TaoBao user behavior data using machine learning (Adaboost, K-means). Achieved 34% precision rate in multi-class classification.

A lightweight, layered Agent framework for Python. Minimal API with Agent, Session, @tool. 26 model providers, 9 core tools, skills framework, and a terminal AI coding agent (Quenda Code).

A fully Python spell correction tool inspired by JamSpell. Supports custom language models, dictionary filtering, and n-gram language model training. Pip-installable with extensible architecture.