ZhuLing is a SpringBoot 4.1 + Spring AI 2.0 based AI Agent scaffolding that lets Java developers create multi-agent applications with zero code by simply writing YAML configuration files.

Stars

13

7-day growth

No data

Forks

0

Open issues

0

License

Apache-2.0

Last updated

2026-07-28

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It provides a production-ready, DDD hexagonal architecture for building AI agents with built-in observability, MCP tool support, and a static chat UI, making it easy to bootstrap complex multi-agent systems without writing boilerplate code.

Who it is for

  • Java developers building AI-powered applications
  • Development teams wanting to quickly prototype multi-agent chatbots
  • Architects evaluating Spring-based AI agent frameworks
  • DevOps engineers seeking an observable and configurable agent runtime

Use cases

  • Rapidly prototyping a conversational agent with custom tools and skills
  • Building multi-agent systems with isolated runtimes and shared infrastructure
  • Integrating MCP-based remote or local tools into a Spring Boot application
  • Debugging and monitoring agent conversations via built-in observability and replay

Strengths

  • Zero-code agent definition using YAML configuration
  • Support for multiple MCP modes (Local, SSE, Stdio) and Skills script execution
  • Comprehensive observability with token stats, tool telemetry, and trace IDs
  • Built-in static chat UI that requires no separate deployment

Considerations

  • Requires JDK 21+, SpringBoot 4.1, and MySQL (or PostgreSQL 15+), which may be newer than some production environments
  • Advanced features like ReAct, multi-agent coordination, and multimodal support are marked as planned, not yet fully implemented
  • Primarily designed for OpenAI-compatible LLM APIs; other providers may require adaptation

README quick start

铸灵 ZhuLing

铸造 AI 灵魂 —— 基于 SpringBoot 4.1 + Spring AI 2.0 + DDD 六边形架构的 AI Agent 开发脚手架

📖 项目简介

铸灵(ZhuLing)帮助 Java 开发者零代码启动 Agent 应用。只需编写一份 YAML 配置文件,即可获得:

  • ✅ 多 Agent 独立注册与运行时隔离
  • ✅ 统一对话目标选择(Agent / Workflow)
  • ✅ 同步 & SSE 流式对话接口
  • ✅ 多轮会话记忆与历史消息持久化
  • ✅ MCP 工具调用(Local / SSE / Stdio 三种模式)
  • ✅ Skills 脚本包加载与执行
  • ✅ 完整的可观测性(Token 统计、工具遥测、Trace ID、上下文占用比)
  • ✅ 版本化 SSE 事件信封(turn / message / reasoning / tool 生命周期事件)
  • ✅ 内置可观测对话工作台 UI

🖼️ 界面预览

登录

对话目标选择

可观测对话工作台

🏗️ 技术栈

组件版本说明
JDK21支持虚拟线程
SpringBoot4.1.0核心框架
Spring AI2.0.1-SNAPSHOTLLM 调用统一管理
Spring AI Alibaba1.1.2.0Agent 编排扩展
WebFlux仅用于对话流式输出
MyBatis-Plus3.5.17持久层(传统阻塞式)
MySQL8.0+会话 / 消息持久化
MCP SDK2.0.0-M2Model Context Protocol
Jackson2.17.2JSON 序列化

📁 工程结构

zhuling/
├── zhuling-types/            # 公共类型(枚举、异常、通用常量)
├── zhuling-api/              # 接口 DTO / VO 定义
├── zhuling-domain/           # 领域层(核心业务、Port/Repository 接口)
├── zhuling-case/             # 编排层(用例编排、聊天流程)
├── zhuling-infrastructure/   # 基础设施层(DAO、Gateway、Redis、可观测性实现)
├── zhuling-trigger/          # 触发层(HTTP Controller)
├── zhuling-app/              # 启动模块(配置文件、Agent YAML、Skills)
├── ui/                           # 可观测对话工作台(纯静态前端)
└── docs/                         # 设计文档、SQL 脚本

依赖规则Trigger → API → Case → Domain ← Infrastructure,所有依赖向内指向 Domain。

🚀 快速开始

环境要求

  • JDK 21+
  • Maven 3.8+
  • MySQL 8.0+(或 PostgreSQL 15+)

1. 克隆项目

git clone https://github.com/vinist123/zhuling.git
cd zhuling

2. 初始化数据库

创建数据库后,执行以下建表 SQL:

-- Agent 会话表
CREATE TABLE agent_session (
    id VARCHAR(36) PRIMARY KEY,
    target_id VARCHAR(128) NOT NULL,
    target_type VARCHAR(20) NOT NULL DEFAULT 'AGENT',
    user_id VARCHAR(64),
    title VARCHAR(256),
    status VARCHAR(20) DEFAULT 'active',
    message_count INT DEFAULT 0,
    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
    updated_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP
);

-- Agent 消息表
CREATE TABLE agent_message (
    id VARCHAR(36) PRIMARY KEY,
    session_id VARCHAR(36) NOT NULL,
    role VARCHAR(20) NOT NULL,
    content TEXT,
    metadata JSON,
    created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
    FOREIGN KEY (session_id) REFERENCES agent_session(id)
);

3. 修改配置

编辑 `zhuling-a

Description

An AI Agent Development Framework AI Agent 开发脚手架

Related repositories

Similar projects matched by category, topics, and programming language.

makecindy
Featured
makecindy GitHub avatar

cindy

Cindy is an open-source AI agent that runs locally on your machine, integrates multiple AI harnesses and models, and provides memory, skills, and automation to perform real work in your projects and apps.

AI & Machine LearningLarge Language Models
958
uzairansaruzi
Featured
uzairansaruzi GitHub avatar

hermex

Hermex is a native SwiftUI iPhone app that lets you control a self-hosted Hermes AI agent directly from your phone, with no subscriptions, tracking, or third-party relay.

AI & Machine LearningLarge Language Models
941
mereyabdenbekuly-ctrl
Featured
mereyabdenbekuly-ctrl GitHub avatar

clodex-ide

Clodex is an open-source, local-first agentic IDE that combines persistent AI tasks, code, terminal, browser, Git, models, memory, and governed execution in one Electron workspace, currently in technical preview.

AI & Machine LearningAI Agents
859