MemoryScope is a framework that endows large language model (LLM) chatbots with long-term memory capabilities. By utilizing a memory database and a working library, chatbots can store and retrieve memory fragments, leading to personalized user interactions. Through processes like memory retrieval and integration, the chatbot understands and remembers user habits and preferences, delivering a more personalized and coherent conversational experience. MemoryScope supports various model APIs, including OpenAI and Dashscope, and can be combined with existing agent frameworks such as AutoGen and AgentScope, providing extensive customization and scalability.