How I Built Collapse Detection for Persistent AI Agents

F_total is your model's prediction error energy — cross-entropy loss for LLMs, TD error for RL agents. F_survival is the minimum energy required to maintain operational integrity. k(s) is a sensitivity constant that grows with runtime. Quick Start from tci_calculator import TCICalculator from k_estimator import KEstimator k_est = KEstimator ( window_size = 100 ) tci = TCICalculator ( f_survival = 0.35 ) f_total = 0.72 complexity = 0.61 k = k_est . update ( f_total - 0.35 , complexity ) result = tci . compute ( f_total , k ) print ( result ) # TCIResult(tci=0.74, grade='A', stage='Generativity', surplus=0.37) What the Grades Mean Grade TCI Range Stage Action A ≥ 0.60 Generativity Raise exploration B 0.40–0.60 Learning Maintain settings C 0.30–0.40 At Risk Reduce exploration D 0.10–0.30 Collapse Warning Stability mode F < 0.10 Collapse Imminent Load checkpoint Links GitHub: https://github.com/hustle-rent-due/tci-toolkit Paper: https://doi.org/10.5281/zenodo.19263435