Eco-FinOps: a causal-agentic framework for energy-efficient and explainable cloud cost optimization.

Two converging crises-uncontrolled operational expenditure and significant environmental hazards-have been aggravated by the exponential scaling of cloud infrastructure. This has led to a greater focus on the efficiency of Financial Operations (FinOps). Current monitoring methods exhibit a major flaw: passive dashboards require constant human monitoring and lead to alert fatigue, whereas deep learning models require substantial Graphics Processing Unit (GPU) resources and operate as opaque "black boxes." This lack of interpretability contradicts the sustainability goals these tools promise to support. This study proposes Eco-FinOps, a causal-agentic framework that autonomously and energy-efficiently optimizes cloud costs, designed strictly for commodity Central Processing Unit (CPU) environments without discrete GPU requirements. The system uses Polars-based telemetry ingestion, the Peter-Clark (Algorithm) (PC) algorithm for causal graph construction, and DoWhy for effect estimation to mathematically distinguish genuine workload fluctuations from inefficient resource usage. This study targets the "zombie" resource pattern-provisioned instances that utilize only 0.2%-5% CPU while maintaining 60%-90% memory consumption. Furthermore, a LangGraph-coordinated Retrieval-Augmented Generation (RAG) pipeline enables Small Language Models to generate auditable, human-verifiable remediation scripts. Evaluated on five fault-injection scenarios from the Alibaba Cluster Trace dataset, the framework achieves a Precision of 0.89, a recall of 0.86, and an F1-score of 0.87. Causal verification successfully eliminates 39% of false positive anomalies, raising Precision by 38 points over static threshold rules and outperforming neural autoencoder baselines by 15 F1 points.