From Declarative Java to Autonomous Graph Execution
Move beyond fragile prompt chains and opaque loops. Gain durable state checkpoints, parallel fan-out/fan-in branches, and human-in-the-loop governance on top of standard Java & Spring.
ReactAgent opsAgent = ReactAgent.builder()
.name("cloud-sre-agent")
.model(chatModel)
.systemPrompt("You are an autonomous production SRE agent.")
.tools(
mcpClient.resolve("prometheus-query"),
mcpClient.resolve("k8s-rollout-status")
)
.hooks(
ModelCallLimitHook.of(12),
ContextCompressionHook.slidingWindow(16_384)
)
.saver(PostgresCheckpointSaver.create(dataSource))
.build();
AssistantMessage reply = opsAgent.call(
"Diagnose latency spike on payment-service and propose safe rollback",
RunnableConfig.builder().threadId("incident-2026-09").build()
);几行 Java 代码构建生产级 ReAct 智能体
通过流式 Builder API 将大模型推理、MCP 工具集、上下文压缩钩子与持久化检查点组合为可观测的自治智能体循环。
- 原生支持 MCP 工具协议与 Spring AI ToolCallback 自动装配
- 内置 Hook 生命周期拦截(模型调用限流、PII 脱敏、上下文压缩)
- 每次推理与工具调用自动生成可回放的状态快照
Upper-layer agent design, runtime-grade execution
Graph 和 ReAct Agent 承担编排、状态、恢复和协作语义,让复杂 Agent 应用具备可观察、可恢复和可扩展的运行时边界。
ReAct Agent 自治推理引擎
将思考(Reason)、工具行动(Act)与环境反馈(Observe)组织成受控的闭环执行流,内置模型限流、上下文压缩与结构化输出校验。
探索 ReAct Agent →Graph Core 状态图编排
用强类型 OverAllState、条件边(Conditional Edges)、并行分支与嵌套子图描述长周期复杂工作流,兼顾确定性控制与动态智能路由。
探索 Graph Core →持久化检查点与故障自愈
每个节点边界自动持久化状态快照(Memory / Redis / PostgreSQL),支持跨实例故障恢复、状态分叉(Fork)与历史回放。
了解持久化执行 →人在回路(HITL)安全管控
支持在敏感工具或高危节点执行前声明式中断(interruptBefore),人工审批或热修改状态参数后无缝恢复原执行上下文。
查看 HITL 模式 →Studio 嵌入式可视化调试
内嵌交互式调试工作台,实时渲染智能体对话流、StateGraph 拓扑高亮、工具入参/出参及节点级耗时遥测。
启动 Studio 调试 →MCP 协议与多智能体协同网络
原生集成 Model Context Protocol(MCP)工具生态,支持 A2A 远程 Agent 封装,以及 Sequential、Parallel、LlmRouting、Loop 与 Agent-as-tool 编排。
探索多智能体编排 →ARGI Ecosystem
A comprehensive ecosystem for building intelligent applications
ARGI ReAct Agent
Upper-layer framework for ReAct Agent, stateful agent loops, and multi-agent coordination.
ARGI Graph Core
Graph runtime for workflow orchestration, state checkpoints, recovery, and human-in-the-loop execution.
ARGI Studio
Embedded visual debugging studio for agent conversations and graph workflows.
ARGI Extensions
Pluggable ecosystem for model adapters, distributed persistence backends, A2A discovery, MCP registry, and sandboxed tool execution.