haoaaa-111 / taoketong

What is taoketong?

Taoketong is a Next.js application that helps students skip class strategically. Upload a screenshot of your course schedule, and it uses an LLM to analyze teacher behavior patterns, predict when rollcalls will happen, and generate personalized weekly attendance plans. The system models different teacher types (strict, understanding, lazy) and adapts recommendations based on your goals—whether you are prepping for graduate exams, maintaining a delicate GPA for保研, or juggling an internship. It learns from weekly feedback, adjusting risk assessments when you get caught or when teachers change their patterns.

Why is it gaining traction?

The project solves a real pain point for Chinese university students who need to strategically skip classes but lack the data to make informed decisions. Instead of blind guessing, you get evidence-based recommendations that account for teacher personality, classroom size, and historical rollcall data. The multi-agent architecture (context builder, modeler, supervisor, orchestrator) allows the system to handle complex scenarios like schedule conflicts between retaken courses and required political classes.

Who should use this?

University students in China facing competing priorities—particularly those balancing graduate exam prep, internships, or GPA-sensitive situations like保研边缘. It is most useful for students with overloaded schedules who need to maximize their time efficiency. The system includes pre-built personas (考研党, 保研党, 实习党) to simulate different student types, making it useful for testing before committing to a strategy.

Verdict

With only 13 stars and a credibility score of 0.7%, this is an early-stage project with limited community validation. The codebase shows thoughtful architecture and comprehensive scenario testing, but production readiness is unclear—deployment requires LLM API keys and the setup involves seed scripts and manual configuration. Worth watching if you are a Chinese university student, but evaluate carefully before relying on it for high-stakes attendance decisions.