Deploying production-ready multi-agent systems (MAS) in complex industrial environments remains challenging due to limitations in scalability, observability, and autonomous evolution. We present OxyGent, an open-source framework driven by two core novelties: a unified Oxy abstraction and the OxyBank evolution engine. The unified abstraction encapsulates agents, tools, LLMs, and reasoning flows as pluggable atomic components, enabling Lego-like scalable system composition and non-intrusive monitoring. To enhance observability, OxyGent introduces permission-driven dynamic planning that replaces rigid workflows with execution graphs generated at runtime, providing adaptive visualizations. Furthermore, to support continuous evolution, OxyBank serves as an AI asset management platform that drives automated data backflow, annotation, and joint evolution. Empirical evaluations and real-world case studies show that OxyGent provides a robust and scalable foundation for MAS. OxyGent is fully open-sourced under the Apache License 2.0 at https://github.com/jd-opensource/OxyGent.

翻译：在复杂工业环境中部署生产级多智能体系统（MAS）仍面临可扩展性、可观测性及自主演化能力的挑战。本文提出OxyGent——一个由两大核心创新驱动的开源框架：统一的Oxy抽象与OxyBank演化引擎。该统一抽象将智能体、工具、大语言模型（LLM）及推理流程封装为可插拔的原子组件，实现类似乐高积木的可扩展系统组装与非侵入式监控。为增强可观测性，OxyGent引入权限驱动的动态规划机制，用运行时生成的执行图替代刚性工作流，提供自适应可视化能力。此外，为支持持续演化，OxyBank作为AI资产管理平台，驱动自动化数据回流、标注与联合演化。实证评估与实际案例研究表明，OxyGent为MAS提供了稳健且可扩展的基础架构。OxyGent已在Apache License 2.0协议下完全开源，地址为https://github.com/jd-opensource/OxyGent。