[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-workflow-orchestration-zh":3,"seo:pack:workflow-orchestration:zh":82},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":81},"workflow-orchestration","🔄","#7E22CE","stable","稳定","工作流编排","n8n \u002F Prefect \u002F Inngest \u002F Kestra \u002F Activepieces — 把 AI agent 包进定时 \u002F 重试 \u002F 可观测的持久化引擎。",[16,28,35,42,51,59,67,74],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},32,"ab76a229-0dc7-48bc-8b29-95ef9c2c45a9","awesome-n8n-workflow-automation-template-collection-ab76a229","Awesome n8n — Workflow Automation Template Collection","Curated n8n workflow templates for data sync, notifications, CRM automation, and more. Import directly into your n8n instance.","n8n",655,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":22,"view_count":34,"vote_count":24,"lang_type":25,"type":26,"type_label":27},484,"9de58e04-c1b8-401d-ab38-57553197bb55","n8n-code-ai-agent-superpowers-n8n-9de58e04","n8n-as-code — AI Agent Superpowers for n8n","Give your AI agent n8n superpowers with 537 node schemas, 7,700+ templates, and TypeScript workflow definitions. Works with Claude Code, Cursor, VS Code, and OpenClaw. MIT license.",384,{"id":36,"uuid":37,"slug":38,"title":39,"description":40,"author_name":22,"view_count":41,"vote_count":24,"lang_type":25,"type":26,"type_label":27},165,"b7ec9ae7-1144-42f0-9335-a5f40fbd6605","n8n-ai-native-workflow-automation-b7ec9ae7","n8n — AI-Native Workflow Automation","Open-source workflow automation with 400+ integrations and built-in AI capabilities. Build AI agents, RAG pipelines, and automation workflows with a visual editor.",395,{"id":43,"uuid":44,"slug":45,"title":46,"description":47,"author_name":22,"view_count":48,"vote_count":24,"lang_type":25,"type":49,"type_label":50},516,"4635d46c-cbf7-4be7-837e-95818241a46c","n8n-mcp-server-build-automations-ai-1-396-nodes-4635d46c","n8n MCP Server — Build Automations with AI, 1,396 Nodes","MCP server giving AI agents access to 1,396 n8n nodes and 2,709 workflow templates. Build and manage n8n automations through natural language.",285,"mcp","MCP",{"id":52,"uuid":53,"slug":54,"title":55,"description":56,"author_name":57,"view_count":58,"vote_count":24,"lang_type":25,"type":26,"type_label":27},305,"dfa1e8d2-b7e4-467b-b156-41a008ac26a9","prefect-python-workflow-orchestration-dfa1e8d2","Prefect — Python Workflow Orchestration","Prefect orchestrates resilient data pipelines in Python with scheduling, retries, caching, and event-driven automation. 22K+ stars. Apache 2.0.","AI Open Source",326,{"id":60,"uuid":61,"slug":62,"title":63,"description":64,"author_name":65,"view_count":66,"vote_count":24,"lang_type":25,"type":26,"type_label":27},873,"f09e8059-33e5-11f1-9bc6-00163e2b0d79","inngest-durable-ai-workflow-orchestration-f09e8059","Inngest — Durable AI Workflow Orchestration","Run reliable AI workflows with automatic retries and state persistence. Replace queues and scheduling with durable step functions. TypeScript, Python, Go SDKs. 5,200+ stars.","Inngest",302,{"id":68,"uuid":69,"slug":70,"title":71,"description":72,"author_name":57,"view_count":73,"vote_count":24,"lang_type":25,"type":26,"type_label":27},880,"556ae291-349d-11f1-9bc6-00163e2b0d79","kestra-event-driven-orchestration-scheduling-platform-556ae291","Kestra — Event-Driven Orchestration & Scheduling Platform","Kestra is an open-source orchestration platform for scheduling and running complex data pipelines, ETL jobs, and automation workflows with declarative YAML.",338,{"id":75,"uuid":76,"slug":77,"title":78,"description":79,"author_name":57,"view_count":80,"vote_count":24,"lang_type":25,"type":26,"type_label":27},206,"13ddf27d-3f2e-4967-b0ba-8f999942d4e9","activepieces-open-source-ai-workflow-automation-13ddf27d","Activepieces — Open-Source AI Workflow Automation","Open-source workflow automation with 400+ integrations and AI agent support. Visual builder, MCP server compatibility, self-hostable alternative to Zapier. 21K+ stars.",282,"tokrepo install pack\u002Fworkflow-orchestration",{"pageType":83,"pageKey":8,"locale":84,"title":85,"metaDescription":86,"h1":13,"tldr":87,"bodyMarkdown":88,"faq":89,"schema":105,"internalLinks":115,"citations":128,"wordCount":141,"generatedAt":142},"pack","zh","工作流编排栈：n8n \u002F Prefect \u002F Inngest 横评 · TokRepo","8 个生产级工作流引擎 —— n8n \u002F Prefect \u002F Inngest \u002F Kestra \u002F Activepieces，把 AI agent 包进定时 \u002F 重试 \u002F 可观测的持久化层。TokRepo 一条命令装齐。","八个生产级工作流引擎 —— n8n \u002F Prefect \u002F Inngest \u002F Kestra \u002F Activepieces \u002F Trigger.dev \u002F Temporal \u002F Windmill —— 把 AI agent 包进定时、重试、可观测的层。TokRepo 一条命令装好整个栈，告别在 tmux 里跑 Jupyter notebook。","## 这个 pack 装了什么\n\n这个 pack 收齐了 AI 团队在「prompt 套循环」不够用之后会摸到的 **8 个生产级工作流引擎**。每个解决的都是同三件事 —— 调度 \u002F 重试 \u002F 观测 —— 但 ergonomics 不同。按你团队已经在的栈选（Python \u002F Node \u002F 无代码 \u002F JVM）。\n\n| # | 引擎 | 适合场景 |\n|---|---|---|\n| 1 | n8n | 无代码 \u002F 低代码，400+ 集成，可自托管 |\n| 2 | Prefect | Python-first 数据 + AI 工作流，动态 DAG |\n| 3 | Inngest | TypeScript \u002F Node，事件驱动 step function |\n| 4 | Kestra | YAML 声明式，JVM，插件生态 |\n| 5 | Activepieces | 开源 Zapier 替代，分支流程 |\n| 6 | Trigger.dev | 长时 TypeScript job，自带重试 |\n| 7 | Temporal | 分布式工作流原语，认真规模就用它 |\n| 8 | Windmill | 多语言脚本（Python\u002FTS\u002FBash\u002FGo）+ UI |\n\n每个都开源可自托管。多数有 SaaS 托管层，但这个 pack 优先记开源装路径。\n\n## 为什么 AI agent 需要编排\n\nPrompt 第一次跑是确定的，之后每次都是抛硬币。再加个真实动作 —— 调 API、写库、发 Slack —— 「凌晨三点失败一次」就会变成每周固定节目。工作流引擎解决三件事：\n\n1. **幂等**。step 可安全重放。LLM 调用成功但后一步崩了，重试不会重复扣 API 钱\n2. **回退 + 死信**。失败 step 按指数退避重试，再不行落进 DLQ 让人看\n3. **可观测**。每个 step 记录输入、输出、延迟、成本。agent 出怪事时能精确回放它当时看到的上下文\n\n没有这些，你的 agent 就是一个加了步骤的 Jupyter notebook。有这些它才是服务。\n\n## 一条命令装齐\n\n```bash\n# 装整个 pack（8 个引擎的 manifest）\ntokrepo install pack\u002Fworkflow-orchestration\n\n# 或装你团队在用的那个\ntokrepo install n8n\ntokrepo install prefect\ntokrepo install inngest\n```\n\nTokRepo manifest 给你 Docker Compose \u002F Helm 起步配置 + agent 友好默认值（幂等 key、重试策略、观测钩子）。卸载就 `tokrepo uninstall \u003Cslug>`。\n\n## 常见踩坑\n\n- **当重试是无限的**。多数引擎默认重试 3–5 次。如果你的 LLM 服务商正赶上糟糕一小时，你会把预算烧光还是失败。付费 LLM 调用上限设 3 次，失败后路由到更慢的备用模型\n- **幂等 key 设错**。常见错误是用每次重试都变的 `request_id`。用输入 hash 当 key，重试才会针对同一逻辑任务去重\n- **少了 token 成本观测**。普通编排器记录延迟但不记 LLM token 花费。把模型调用包一层，每个 step 输出 `tokens_in \u002F tokens_out \u002F cost_usd` 指标，否则爆预算了你都不知道是哪个工作流干的\n- **调度粒度选错**。基于 cron 的引擎（n8n \u002F Activepieces）拼不过亚分钟触发。要事件驱动亚秒响应，用 Inngest \u002F Trigger.dev \u002F Temporal\n- **引擎跟 agent 同节点**。野的 agent 会把编排器 OOM。引擎放独立节点或容器并设硬内存上限\n\n## 这个 pack 单独不够时\n\n工作流编排是 *持久化* 层。它不给你 agent 本身、LLM 网关或评测。配套：\n\n- **Python Agent Frameworks** —— 真在 step 里跑的 agent 代码\n- **MCP Server Stack** —— 要让 agent 通过 MCP 触发编排器\n- **LLM Eval & Guardrails** —— 在每个工作流里加评测 step，再决定是否上线\n\n四个 pack 一起，才是无人值守 AI 工作流的最小栈。",[90,93,96,99,102],{"q":91,"a":92},"工作流编排免费吗？","本 pack 八个引擎全部开源可自托管。n8n \u002F Prefect \u002F Inngest \u002F Kestra \u002F Activepieces \u002F Trigger.dev \u002F Temporal \u002F Windmill 都发开源 Docker 镜像。代价是引擎要你自己运维 —— DB、队列、扩缩容。多数有 SaaS 托管层（n8n Cloud \u002F Prefect Cloud \u002F Inngest Cloud），不想运维就付钱。",{"q":94,"a":95},"跟 cron + Python 脚本比怎么样？","cron 没有重试、没有幂等、没有观测、没有 DLQ。脚本要么成功要么下次再跑。AI agent 调付费 API 还有副作用，cron 不安全。这个 pack 最便宜的版本 —— Inngest 免费层 + Vercel function —— 大约就是 cron 等价表面但带重试和 UI，且免费。",{"q":97,"a":98},"Claude Code 或 Cursor 的 agent 能用吗？","能，但是间接的。Claude Code 和 Cursor 是交互式编码 agent，跑在你笔记本上。工作流引擎跑在服务器上。模式是：Claude Code 写 agent 代码，你把代码包进 step function（Inngest \u002F Prefect task），引擎按计划跑。引擎不在乎 step 里调的是 Claude API。",{"q":100,"a":101},"跟 Apache Airflow 有啥区别？","Airflow 在用，但它的 DAG-as-Python 模型和慢调度心跳让它对需要事件驱动亚秒响应、频繁动态分支的 AI agent 不友好。Prefect \u002F Inngest \u002F Temporal 都是「现代 Airflow」起家。我们没收 Airflow 是因为团队拿它跑 AI agent 半年内都会迁出去。",{"q":103,"a":104},"上线该提前防的运维坑？","反压。下游 LLM 服务商一慢，你编排器队列会膨胀把引擎 OOM。生产规模前先设每队列并发上限和全局出站 LLM 调用限速器。Inngest 和 Trigger.dev 自带；n8n 和 Prefect 要显式配。",{"@context":106,"@type":107,"name":108,"description":109,"numberOfItems":110,"publisher":111},"https:\u002F\u002Fschema.org","CollectionPage","Workflow Orchestration","n8n, Prefect, Inngest, Kestra, Activepieces — durable workflow engines that wrap AI agents in cron, retries, and observability.",8,{"@type":112,"name":113,"url":114},"Organization","TokRepo","https:\u002F\u002Ftokrepo.com",[116,120,124],{"url":117,"anchor":118,"reason":119},"\u002Fzh\u002Fpacks\u002Fpython-agent-frameworks","Python Agent 框架","在这些编排器里跑的 agent 层",{"url":121,"anchor":122,"reason":123},"\u002Fzh\u002Fpacks\u002Fmcp-server-stack","MCP 服务器全家桶","把编排器触发器以 MCP 暴露给 AI agent",{"url":125,"anchor":126,"reason":127},"\u002Fzh\u002Fpacks\u002Fllm-eval-guardrails","LLM 评测 & 护栏","把评测步骤接进持久化工作流",[129,133,137],{"claim":130,"source_name":131,"source_url":132},"Prefect provides durable task scheduling, retries, and observability for Python workflows","Prefect docs","https:\u002F\u002Fdocs.prefect.io\u002F",{"claim":134,"source_name":135,"source_url":136},"n8n is a fair-code workflow automation platform with 400+ integrations","n8n GitHub","https:\u002F\u002Fgithub.com\u002Fn8n-io\u002Fn8n",{"claim":138,"source_name":139,"source_url":140},"Inngest provides durable functions and event-driven step orchestration","Inngest docs","https:\u002F\u002Fwww.inngest.com\u002Fdocs",463,"2026-05-02T15:00:00Z"]