This paper introduces an interactive Change-Agent for comprehensive remote sensing change interpretation and analysis. The Change-Agent integrates a multi-level change interpretation (MCI) model as its "eyes" and a large language model (LLM) as its "brain". The MCI model contains two branches: pixel-level change detection and semantic-level change captioning. A novel BI-temporal Iterative Interaction (BI3) layer is proposed to enhance the model's discriminative feature representation capabilities. The Change-Agent is trained on the LEVIR-MCI dataset, which contains bi-temporal images, change detection masks, and descriptive captions. Experiments demonstrate the effectiveness of the MCI model in achieving both change detection and change description simultaneously, highlighting the promising application value of the Change-Agent in facilitating comprehensive interpretation of surface changes. The Change-Agent can follow user instructions to provide insightful analysis, such as change detection, change captioning, change object counting, and change cause analysis. The LLM serves as the brain of the Change-Agent, enabling it to understand user intentions and provide customized change interpretation and intelligent analysis services. The Change-Agent bridges the gap between users and remote sensing expertise, offering a new avenue for intelligent remote sensing applications. The proposed method provides a comprehensive and accurate interpretation of surface changes, reducing the workload and time costs for researchers while enhancing the efficiency and convenience of interaction between users and remote sensing data. The Change-Agent is publicly available at https://github.com/Chen-Yang-Liu/Change-Agent.This paper introduces an interactive Change-Agent for comprehensive remote sensing change interpretation and analysis. The Change-Agent integrates a multi-level change interpretation (MCI) model as its "eyes" and a large language model (LLM) as its "brain". The MCI model contains two branches: pixel-level change detection and semantic-level change captioning. A novel BI-temporal Iterative Interaction (BI3) layer is proposed to enhance the model's discriminative feature representation capabilities. The Change-Agent is trained on the LEVIR-MCI dataset, which contains bi-temporal images, change detection masks, and descriptive captions. Experiments demonstrate the effectiveness of the MCI model in achieving both change detection and change description simultaneously, highlighting the promising application value of the Change-Agent in facilitating comprehensive interpretation of surface changes. The Change-Agent can follow user instructions to provide insightful analysis, such as change detection, change captioning, change object counting, and change cause analysis. The LLM serves as the brain of the Change-Agent, enabling it to understand user intentions and provide customized change interpretation and intelligent analysis services. The Change-Agent bridges the gap between users and remote sensing expertise, offering a new avenue for intelligent remote sensing applications. The proposed method provides a comprehensive and accurate interpretation of surface changes, reducing the workload and time costs for researchers while enhancing the efficiency and convenience of interaction between users and remote sensing data. The Change-Agent is publicly available at https://github.com/Chen-Yang-Liu/Change-Agent.