# Agency Orchestrator

🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 267 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 11 LLM providers (7 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。

Repository: https://github.com/jnMetaCode/agency-orchestrator
Canonical: https://ross.abutalabs.com/products/agency-orchestrator
Homepage: https://ao.aiolaola.com
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: ai-agents, claude, crewai-alternative, deepseek, multi-agent, ollama, orchestrator, workflow, openai, codex, copilot, cursor, gemini-cli, mcp-server, agent-orchestration, autogen-alternative, langgraph-alternative, no-api-key, yaml-workflow, agency-agents
Last push: 2026-08-26T14:27:40+00:00
Link (homepage): https://ao.aiolaola.com

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 11
- inputs: {"age_days": 165, "days_push": 7, "days_rel": 12, "gap_med": 0, "n_releases_24m": 22}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2134, forks 280 (observed 2026-08-28T04:06:17.404327+00:00)

## What it is
Agency Orchestrator is a multi-agent YAML workflow engine and desktop client that lets a single sentence trigger multiple AI expert roles to collaborate automatically via DAG-based parallelism. It pairs with a library of 267+ Chinese and 184+ English plug-and-play AI role definitions usable across 18 tools like Claude Code, Cursor, and Copilot.

## Use cases
- orchestrate multiple AI agents from one sentence
- run zero-code multi-agent workflows defined in YAML
- assemble a team of AI expert roles for engineering, design, or marketing tasks
- run China-market AI agents for Xiaohongshu, Douyin, WeChat, Feishu, and DingTalk operations
- replace CrewAI, LangGraph, or AutoGen with a no-code orchestrator
- use LLM providers without API keys via subscription-based access
- manage a unified AI agent workbench for a team or one-person company

## When to choose
- you want plug-and-play AI expert personas with automatic DAG-based collaboration and no coding
- you need Chinese-market-specific agents or a Chinese-language agent library
- you want a native desktop app that works without installing Node or managing API keys

## When to avoid
- you need fully programmatic, code-level control over agent internals and custom tooling
- you require a battle-tested framework for production-critical multi-agent systems at large scale
- you only need a single-agent chatbot without orchestration

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, workflow-automation, llm-inference, prompt-engineering, mcp
- domain: large-language-models, developer-tools
- platform: windows, cross-platform
- tags: multi-agent, agent-orchestration, yaml-workflow, dag, no-code, ai-roles, claude-code, cursor, copilot, chinese-market, crewai-alternative, langgraph-alternative, no-api-key, one-person-company, ai-agents, automation, macos, linux, desktop, nodejs

## Member repositories
- jnMetaCode/agency-orchestrator (main) score 81
- jnMetaCode/agency-agents-zh (plugin) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:17.404327+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:59:23.310595+00:00, confidence not recorded.
  - readme: https://github.com/jnMetaCode/agency-orchestrator (fetched 2026-08-28T04:06:17.404327+00:00, sha feab2fdc4b87)
  - homepage: https://ao.aiolaola.com (fetched 2026-08-29T07:58:19.436774+00:00, sha 35ab61c27dc5)
  - registry_npm: https://registry.npmjs.org/agency-orchestrator (fetched 2026-08-29T07:58:19.449222+00:00, sha 094b0053919c)
- Data as of 2026-08-30T08:39:29.467469+00:00.