OpenAgentFlow
Java AI Agent, Spring Boot 3, Vue3, RAG, Tool Calling, MCP, LLM, OpenAI-compatible, Milvus, MySQL, Redis, Workflow, Trace, Evaluation, Cost Governance. OpenAgentFlow-Java 是开源 Java AI Agent 工作流平台，核心链路自研，支持智能体编排、知识库问答、文档切片、向量检索、工具调用、MCP 接入、可视化工作流、运行追踪、模型评测、Token 统计、成本治理和企业级二次开发。
新任务会按负载进入 .document、.evaluation、.integration、.maintenance 分类 Topic，对应重试 Topic 使用相同后缀。Worker 每 20 秒刷新心跳，每次接管递增 lock_version；旧 Worker 无法提交新执行代次的结果。执行失败后进入 5 秒和 30 秒重试 Topic，超过最大次数后进入死信 Topic；Outbox 独立重试 Broker 发送，补偿调度器处理遗留待执行任务和心跳超时任务。调试台 SSE、单次 Agent、多 Agent 和工作流运行保留实时响应链路。
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/wuruiwurui-openagentflow — read its card at https://meshkore.com/agent/wuruiwurui-openagentflow/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/wuruiwurui-openagentflowFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/wuruiwurui-openagentflow/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own OpenAgentFlow?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.