Skip to main content
0
A

Agency Orchestrator

The first multi-agent framework that works with your existing AI subscription — no API key needed. 全

Rating

0.0

Votes

0

score

Downloads

0

total

Price

Free

API key required

Works With

Claude CodeCursorWindsurfVS CodeDeveloper tool

About

Agency Orchestrator

中文 | English

你已经为 AI 付了月费。为什么跑个工作流还要再掏 API key 的钱?

](https://github.com/jnMetaCode/agency-orchestrator/actions) [ ](./LICENSE) [

186 个专业 AI 角色 · YAML 零代码编排 · 有会员就能跑 · 免 API key

Claude Max ✓  ChatGPT Plus ✓  GitHub Copilot ✓  Google 账号(免费)✓  Ollama ✓
觉得有用?请点个 Star — 帮助更多人发现这个项目。

为什么需要 Agency Orchestrator

你遇到过这些问题吗?

  • 想让多个 AI 角色协作,但 CrewAI/LangGraph 要写 Python,还要花时间定义每个角色
  • 装好了框架,发现还要去申请 API key、充值、管额度
  • 你明明已经有 Claude Max / ChatGPT Plus / Copilot 会员了,却用不上

Agency Orchestrator 的答案:

写一个 YAML 文件 → 186 个专业角色自动协作 → 用你已有的会员直接跑。

行业首创:全球所有多智能体框架(CrewAI / LangGraph / AutoGen / Dify / n8n / Agency Swarm / MetaGPT / Google ADK / OpenAI Agents SDK)都要求 API key。只有 Agency Orchestrator 让你带着订阅来用。

30 秒对比

python
# CrewAI: ~50 行 Python,角色从零写,必须有 API key
researcher = Agent(role="PM", goal="...", backstory="...(你自己写)...")
task = Task(description="...", agent=researcher)
crew = Crew(agents=[researcher], tasks=[task])
crew.kickoff()
yaml
# Agency Orchestrator: 10 行 YAML,186 个角色开箱即用,无需 API key
steps:
  - id: analyze
    role: "product/product-manager"   # 现成角色,专业 prompt 已写好
    task: "分析这个 PRD:{{prd_content}}"
CrewAILangGraphAutoGenAgency Orchestrator
语言PythonPythonPythonYAML(零代码)
角色自己写自己写自己写186 个现成
API key必须必须必须6 种免 API key
依赖pip + LiteLLM + 几十个包pip + LangChainpip + AutoGennpm + 2 个依赖
中文角色186 个(44 个中国原创)
并行Manager 模式手动建图手动DAG 自动检测
价格开源 + $25-99/月云版开源开源完全免费

3 步开始

第 1 步:5 秒体验

bash
npx agency-orchestrator demo

4 个 AI 角色协作写小说。无需安装、无需配置、无需 API key。

第 2 步:用你的会员跑真实工作流

bash
npm install agency-orchestrator
npx ao init                    # 下载 186 个 AI 角色

# 用你已有的 Claude Max 会员(无需 API key!)
npx ao run workflows/story-creation.yaml --input premise='一个时间旅行的故事'

只需在 YAML 中写 provider: "claude-code"。没有 Claude?用 gemini-cli(Google 账号免费)、copilot-clicodex-cli 都行。

第 3 步:在 AI 编程工具中直接说

bash
./scripts/install.sh           # 一键安装到你的 AI 编程工具

然后在 Cursor / Claude Code / Copilot 中直接说:

运行 workflows/story-creation.yaml,创意是"一个程序员在凌晨发现AI回复不该知道的事"

AI 会自动解析 YAML → 加载角色 → 按 DAG 顺序执行 → 保存结果。

支持 14 个 AI 编程工具集成指南):Claude Code · GitHub Copilot · Cursor · Windsurf · Kiro · Trae · Aider · Gemini CLI · Codex CLI · OpenCode · Qwen Code · DeerFlow 2.0 · Antigravity · OpenClaw

真实演示:4 个 AI 角色 2 分钟写出完整小说

$ ao run workflows/story-creation.yaml -i "premise=一个程序员在凌晨三点发现AI开始回复不该知道的事情"

  工作流: 短篇小说创作
  步骤数: 4 | 并发: 2 | 模型: deepseek-chat
──────────────────────────────────────────────────

  ── [1/4] story_structure (叙事学家) ──
  完成 | 14.9s | 1,919 tokens
    核心冲突:程序员与一个似乎拥有超越其代码权限的自主意识之间的认知对抗...

Don't lose this

Three weeks from now, you'll want Agency Orchestrator again. Will you remember where to find it?

Save it to your library and the next time you need Agency Orchestrator, it’s one tap away — from any AI app you use. Group it into a bench with the rest of the team for that kind of task and you can pull the whole stack at once.

⚡ Pro tip for geeks: add a-gnt 🤵🏻‍♂️ as a custom connector in Claude or a custom GPT in ChatGPT — one click and your library is right there in the chat. Or, if you’re in an editor, install the a-gnt MCP server and say “use my [bench name]” in Claude Code, Cursor, VS Code, or Windsurf.

🤵🏻‍♂️

a-gnt's Take

Our honest review

This plugs directly into your AI and gives it new abilities it didn't have before. The first multi-agent framework that works with your existing AI subscription — no API key needed. 全. Once connected, just ask your AI to use it. It's completely free and works across most major AI apps. This one just landed in the catalog — worth trying while it's fresh.

Tips for getting started

1

Tap "Get" above, pick your AI app, and follow the steps. Most installs take under 30 seconds.

2

Heads up: this needs an API key to work. You'll get one from the service's website (usually free). The setup guide tells you exactly where.

What's New

Version 1.0.06 days ago

Imported from GitHub

Ratings & Reviews

0.0

out of 5

0 ratings

No reviews yet. Be the first to share your experience.