With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges in developing robust and efficient multi-agent applications. To tackle these challenges, we propose AgentScope, a developer-centric multi-agent platform with message exchange as its core communication mechanism. Together with abundant syntactic tools, built-in resources, and user-friendly interactions, our communication mechanism significantly reduces the barriers to both development and understanding. Towards robust and flexible multi-agent application, AgentScope provides both built-in and customizable fault tolerance mechanisms while it is also armed with system-level supports for multi-modal data generation, storage and transmission. Additionally, we design an actor-based distribution framework, enabling easy conversion between local and distributed deployments and automatic parallel optimization without extra effort. With these features, AgentScope empowers developers to build applications that fully realize the potential of intelligent agents. We have released AgentScope at https://github.com/modelscope/agentscope, and hope AgentScope invites wider participation and innovation in this fast-moving field.

翻译：随着大语言模型（LLMs）的快速发展，多智能体应用取得了显著进展。然而，协调智能体协作的复杂性以及大语言模型不稳定的性能，给开发稳健高效的多智能体应用带来了显著挑战。为应对这些挑战，我们提出AgentScope，一个以开发者为中心的多智能体平台，其核心通信机制为消息交换。结合丰富的语法工具、内置资源和用户友好的交互方式，我们的通信机制显著降低了开发和理解的门槛。为了实现稳健且灵活的多智能体应用，AgentScope既提供了内置的又支持自定义的容错机制，同时还配备了系统级支持，用于多模态数据的生成、存储和传输。此外，我们设计了一种基于actor的分布式框架，能够轻松实现本地部署与分布式部署之间的转换，并无需额外努力即可自动进行并行优化。凭借这些特性，AgentScope使开发者能够构建充分释放智能体潜力的应用。我们已在https://github.com/modelscope/agentscope上发布了AgentScope，并希望AgentScope在这个快速发展的领域中吸引更广泛的参与和创新。