AI Skill Hub 强烈推荐:AgentFlow 是一款优质的Agent工作流。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
AgentFlow 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
AgentFlow 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 克隆仓库 git clone https://github.com/datallmhub/agentflow4j cd agentflow4j # 查看安装说明 cat README.md # 按 README 完成环境依赖安装后即可使用
# 查看帮助 agentflow4j --help # 基本运行 agentflow4j [options] <input> # 详细使用说明请查阅文档 # https://github.com/datallmhub/agentflow4j
# agentflow4j 配置说明 # 查看配置选项 agentflow4j --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export AGENTFLOW4J_CONFIG="/path/to/config.yml"
Build AI agents you can trust in production.
AgentFlow4J is a framework and runtime for governed, stateful multi-agent systems on the JVM.
Human approvals · Checkpoints · Budget controls · Tool policies · Durable execution
---
| Capability | What it does | AgentFlow4J |
|---|---|---|
| **Multi-agent orchestration** | Build agent teams with routing and fan-out | AgentGraph, CoordinatorAgent, ParallelAgent |
| **Governance** | Control what agents can call, change, or spend | ToolPolicy, StatePolicy, BudgetPolicy, ApprovalGate |
| **Durable execution** | Survive restarts, resume from last checkpoint | JdbcCheckpointStore, RedisCheckpointStore |
| **Human-in-the-loop** | Pause before critical actions, resume on approval | ApprovalGate |
| **Resilience** | Classify failures, retry smart, route to fallback | RetryPolicy, FailureClassifier, BudgetAwareRouter |
| **Observability** | Metrics, run logs, streaming events | Micrometer, RunLog, Flux<AgentEvent> |
Two API levels: Squad API for dynamic routing with minimal setup, Graph API for explicit flows, loops and full control. See Two API levels.
---
See Getting started for Maven/Gradle setup and module reference.
---
git clone https://github.com/datallmhub/agentflow4j.git
cd agentflow4j
mvn install -DskipTests -q
mvn -pl agentflow4j-samples exec:java
Runs SupportTriageDemo by default: a governed multi-agent workflow with ToolPolicy and ApprovalGate active. No API key required; falls back to deterministic stubs, or calls Mistral when MISTRAL_API_KEY is set.
See all samples to explore other demos.
▶ See it in action: live demo of a sample implementation, a governed multi-agent customer-support workflow.
---
高质量的Java AI工作流框架
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,AgentFlow 是一款质量优秀的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | agentflow4j |
| 原始描述 | 开源AI工作流:Build multi-agent AI workflows in Java. Run them in production with security, go。⭐36 · Java |
| Topics | agent-orchestrationai-agentsjava |
| GitHub | https://github.com/datallmhub/agentflow4j |
| License | Apache-2.0 |
| 语言 | Java |
收录时间:2026-06-08 · 更新时间:2026-06-08 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端