{"data":{"slug":"jnmetacode-agency-orchestrator","name":"agency-orchestrator","tagline":"🚀 One sentence → multi-AI-role collaboration → complete plan in minutes","github_url":"https://github.com/jnMetaCode/agency-orchestrator","owner":"jnMetaCode","repo":"agency-orchestrator","owner_avatar_url":"https://avatars.githubusercontent.com/u/12096460?v=4","primary_language":"TypeScript","stars":2274,"forks":303,"topics":["agency-agents","agent-orchestration","ai-agents","autogen-alternative","claude","codex","copilot","crewai-alternative","cursor","deepseek","gemini-cli","langgraph-alternative","mcp-server","multi-agent","no-api-key","ollama","openai","orchestrator","workflow","yaml-workflow"],"archived":false,"github_pushed_at":"2026-09-16T10:32:53+00:00","maintenance_label":"Very active","stars_delta_30d":202,"url":"https://www.graphcanon.com/tools/jnmetacode-agency-orchestrator","markdown_url":"https://www.graphcanon.com/tools/jnmetacode-agency-orchestrator.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jnmetacode-agency-orchestrator","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jnmetacode-agency-orchestrator","description":"🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 276 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 15 LLM providers (11 key-free). 一句话组建你的「一人公司」AI 专家团队，几分钟交付完整方案；验收自动核验，网页 / 桌面 / Docker 全渠道。","homepage_url":"https://ao.aiolaola.com","license":"Apache-2.0","open_issues":7,"watchers":14,"ai_summary":"Agency Orchestrator is an AI workflow orchestrator that enables automatic collaboration among multiple AI agents to execute tasks based on user inputs. It supports various large language models and allows for zero-code YAML configuration.","readme_excerpt":"# Agency Orchestrator\n\n**中文** | [English](./README.en.md)\n\n> **一句话，让多个 AI 角色自动协作，几分钟出完整方案。**\n>\n> **也是你的「一人公司」：你当老板，AI 当团队——自动组队、重大决策请你签字、按验收标准交付。**\n\n\n\n\n\n\n**一句话出结果 · 276 个专业 AI 角色 · YAML 零代码 · 15 种大模型 · 支持 key（推荐 DeepSeek），也有 11 种免 key 方式**\n\n> 📖 [完整上手教程](https://mp.weixin.qq.com/s/XcGbkMb6TM6NLQiL7ICwbw)（从安装到实战，10 分钟上手）&nbsp;·&nbsp; 🎓 **官方配套课程**：[AI 专家团队实战](https://aiolaola.com/course/ai-agency?utm_source=github&utm_campaign=orchestrator)（35 节免费，桌面端零代码：单兵点名→自动组队→一人公司全流程，含官方评测的诚实用法边界）· 另有 [AI 内容流水线](https://aiolaola.com/course/ai-pipeline?utm_source=github&utm_campaign=orchestrator)（31 节免费——**用 AO 产线真实生产两门课的全过程留档**：蒸馏、换角色审核、机械闸门、断点续跑，含七类翻车现场）＋ [从零学会 AI 编程](https://aiolaola.com/?utm_source=github&utm_campaign=orchestrator)（182 节）＋ [从零构建 AI 智能体](https://aiolaola.com/course/ai-agent?utm_source=github&utm_campaign=orchestrator)（40 节）（站上共 13 门课、648 节，**全部 ¥0**——另有 AI 绘画 / 写小说 / 漫剧 / 量化 / DeepSeek / 深度专注 等）\n\n> 觉得有用？请点个 **Star** — 帮助更多人发现这个项目。\n\n<p align=\"center\">\n  <img src=\"./demo-studio-zh.gif\" alt=\"网页 Studio：一句话，AI 自动组队\" width=\"820\"><br/>\n  <em>网页 Studio：打一句话，AI 自动从 200+ 专家里组队并运行</em>\n</p>\n\n---\n\n## 网页 Studio（图形界面）\n\n不想敲命令行？本地跑一条 `ao web`，浏览器里勾选专家、运行工作流、查看产物、实时介入——全程图形界面，全中英双语。\n\n**先跑起来**\n\n- **零配置首跑** —— 本机已登录 Claude Code / Gemini CLI 等？AO 自动探测并直接用，连 API key 都不用配\n- **AI 自动组队** —— 不知道选哪些专家？角色页一句话、不选角色，AI 从全部专家里挑人组队并运行\n- **「一人公司」系列模板** —— 做产品 / 做内容 / 做投研 + 全员大会；关键步骤带验收标准（`acceptance`），投研含老板签字闸门，交付的是可验收的工作成果，不承诺奇迹\n\n**改成你要的样子**\n\n- **可视化画布** —— 拖拽节点 / 连线（自动防环）/ 改任务与角色 / 保存；运行时节点按状态实时点亮\n- **我的角色 + 提示生成** —— 「提示生成」页产出的 system prompt 一键存为自建角色（`~/.ao/roles`），组队页「我的」分类直接用；角色卡可 ☆ 收藏常用\n- **多语言角色库** —— `npm i agency-agents-ko`（ko / ru / pt-br / id / ar）后，Studio「角色库」下拉一键切换，工作流 `agents_dir` 写包名即可跑\n- **创意库** —— 图片 **1500+** 条提示词（229 条策展 + 1275 条扩充池，可搜索 / 分类 / 一键复制，配了 key 直接出图）＋ 视频 **76** 条（22 个 5 段式题材模板带变量表、6 个可复用构件、48 条社区成品单条）；扩充池点了才加载，不拖慢首屏\n- **出片流水线** —— `type: image` 文生图、`type: video` 文生视频 / **图生视频**（首帧 = 上游定妆图，角色不变脸）、`type: concat` 本机 ffmpeg 多镜合成、15 个预设的**风格库**；内置模板「短剧流水线（3 镜）」把它们串成 剧本 → 定妆图 → 三镜并行出片 → 合成 → 交付页。图片/视频供应商在 Studio 右上角统一切换，换赞助商就是换下拉，按秒计费看得见\n\n**跑完把成果发出去**\n\n- 🆕 **可分享报告页** —— 运行详情一键「分享页」（CLI 为 `ao report`）：专家分工时间线 + 每步产出的自包含单文件 HTML，直接发群里，对方无需装 AO\n- 🆕 **结果群推送** —— `ao run --notify <webhook>` 跑完自动推到钉钉 / 飞书 / 企业微信群（按域名自动适配机器人格式），配合 cron 就是\"AI 团队每天定点交活\"\n- 🆕 **社区模板** —— 工作流页「社区模板」分区：收录制远程清单一键导入（保存前经引擎校验），你的好工作流也可以投稿给所有用户用\n\n**只有 AO 有的一件事：安全切换服务商 + 一键急救**\n\n把系统 Claude 一键切到任意中转，写进全局配置、**任意终端 `claude` 直接生效**——写前**自动备份**、可**一键切回官方登录**、绝不碰你的官方 OAuth 凭据。被别的切换器或手改写坏了 `~/.claude`（假 token 顶掉登录、整机 CLI 用不了）？「系统 Claude Code 体检」卡一键修复。\n\n> 别的工具什么都能切，但可能把你环境切坏；**AO 只做一件事——安全地切，还能修好被切坏的。**\n\n<p align=\"center\">\n  <img src=\"./docs/screenshots/studio-workflows-zh.png\" alt=\"Studio · 工作流模板：内置模板一键运行\" width=\"800\"><br/>\n  <em>工作流：内置模板一键运行，也能对比多个模板</em>\n</p>\n\n<p align=\"center\">\n  <img src=\"./docs/screenshots/studio-roles-zh.png\" alt=\"Studio · 角色组队：276 位专家按领域分组，公司经营部七位高管置顶\" width=\"800\"><br/>\n  <em>角色组队：☆ 收藏常用、「我的」自建角色，一键切换多语言角色库（图为韩语库）</em>\n</p>\n\n> 启动：`ao web`（本地，密钥只存你自己机器、绝不外传）。也有 [桌面客户端下载](https://github.com/jnMetaCode/agency-orchestrator/releases/latest)（Electron · macOS / Windows / Linux）。\n> 英文界面同样完整 → 见 [English README](./README.en.md)。\n\n---\n\n## 一句话出结果\n\n也可以纯命令行——一条命令，一句话出结果：\n\n```bash\nao compose \"我是一个程序员，想用AI做自媒体副业，目标月入2万，帮我做完整规划\" --run\n```\n\n<p align=\"center\">\n  <img src=\"./demo-zh.gif\" alt=\"ao compose 命令行演示\" width=\"700\">\n</p>\n\n5 个 AI 角色自动分工协作：\n\n```\n  工作流: 程序员AI自媒体副业规划\n  步骤数: 5 | 模型: claude-code\n  参与者: 🔭 趋势研究员 | 📱 平台分析师 | 💰 财务规划师 | ✍️ 内容策略师 | 📋 执行规划师\n──────────────────────────────────────────────────\n\n  ✅ 🔭 趋势研究员    31.3s  → 6个赛道竞争度/变现天花板/AI提效倍数对比\n  ✅ 📱 平台分析师    32.0s  → 6大平台三维评分，推荐\"小红书+公众号\"组合\n  ✅ 💰 财务规划师    31.8s  → 月入2万拆解：课程¥11,880 + 社群¥2,488 + 咨询¥4,000\n  ✅ ✍️ 内容策略师    44.6s  → 20个选题 + 4套标题模板 + 内容SOP\n  ✅ 📋 执行规划师    42.2s  → 90天行动计划，精确到每天做什么\n\n==================================================\n  完成: 5/5 步 | 182.1s | 6,493 tokens\n==================================================\n```\n\n**不用写代码，不用写配置，不用选角色。** 一句话 → AI 自动拆解任务 → 从 276 个角色中匹配 → 按 DAG 并行执行 → 输","github_created_at":"2026-03-21T18:32:02+00:00","created_at":"2026-07-15T11:18:55.173961+00:00","updated_at":"2026-09-20T05:18:38.91265+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"agency-agents","name":"agency-agents"},{"slug":"agent-orchestration","name":"agent-orchestration"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"yaml-workflow","name":"yaml-workflow"}],"trust":{"provenance":{"is_fork":false,"github_id":1188191061,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:18:36.684Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":15,"days_since_push":3,"last_release_at":"2026-08-28T13:52:44Z","stars_delta_30d":202,"open_issues_delta_30d":-3},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":28,"high_count":0,"last_scan_at":"2026-07-15T11:18:56.729Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"package.json:@modelcontextprotocol/*","observed_at":"2026-09-20T05:18:37.706Z","server_manifest":true},"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:18:37.706Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-20T05:18:37.706Z","managed_saas":false},"has_cli":{"value":true,"source":"package.json:bin|scripts","observed_at":"2026-09-20T05:18:37.706Z"},"languages":{"value":["typescript","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T05:18:37.706Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-20T05:18:37.706Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T05:18:37.706Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You require automatic collaboration across a wide range of pre-defined expert roles (216+) to execute specific tasks efficiently.","Your task involves complex decision-making that benefits from multiple viewpoints such as product, technology, finance, and marketing provided by diverse AI agents."],"when_not_to_use":["If your workflow is simple or requires minimal collaboration; a single AI agent might suffice.","When you are working in an environment where there's high sensitivity around software licensing and the Apache-2.0 license poses compliance concerns."],"source":"enrich:decision_facts","observed_at":"2026-07-16T19:47:02.091Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Agency Orchestrator is an AI workflow orchestrator that automatically collaborates among multiple AI agents based on user inputs, supports various large language models, and allows for zero-code YAML configuration."}]}}