---
title: "Deploy Agency Orchestrator AI Team"
description: "One sentence in, full plan out: multi-agent AI team with 270+ roles"
category: "AI/ML"
url: https://railway.com/deploy/agency-orchestrator-ai-team
---

# Deploy Agency Orchestrator AI Team

One sentence in, full plan out: multi-agent AI team with 270+ roles

**[Deploy Agency Orchestrator AI Team on Railway](https://railway.com/template/agency-orchestrator-ai-team)**

Machine-readable deploy manifest (JSON, validated by TemplateCI): https://railway.com/deploy/agency-orchestrator-ai-team/manifest.json

- **Creator:** My Projects
- **Category:** AI/ML

## Template content

### agency-orchestrator https://raw.githubusercontent.com/jnMetaCode/agency-orchestrator/main/website/public/logo/ao-app-icon.svg

- **Image:** ghcr.io/jnmetacode/agency-orchestrator:latest
- **Health check:** /
- **Public domain:** Yes

## Documentation

# Deploy and Host Agency Orchestrator AI Team on Railway

[Agency Orchestrator](https://github.com/jnMetaCode/agency-orchestrator) turns **one sentence into a full plan**: it auto-assembles a team from 270+ expert AI roles (CEO, CTO, PM, designer, marketer, engineer…), runs them as a multi-agent workflow, asks for your sign-off on big decisions, and delivers against acceptance criteria. Workflows are zero-code YAML, and the **Web Studio** lets you run, review and share everything from the browser.

## About Hosting Agency Orchestrator

This template runs the official `ghcr.io/jnmetacode/agency-orchestrator` image (`ao web` Studio, port 8088) with:

- a persistent volume at `/data` for provider settings, workflows and run outputs
- **`AO_WEB_TOKEN`** — a randomly generated access token; every `/api/*` call requires it, so your saved provider keys can't be used by strangers
- **`AO_ALLOWED_HOSTS`** set to your Railway domain (Studio rejects unknown Host headers to prevent DNS-rebinding attacks)

**After deploy:**
1. Copy `AO_WEB_TOKEN` from the service's *Variables* tab.
2. Open `https://YOUR-RAILWAY-DOMAIN/?token=YOUR_TOKEN` once — the token is stored in that browser tab and removed from the address bar.
3. Add an LLM provider in **Providers** (DeepSeek recommended; OpenAI, Claude, Gemini, Kimi, GLM, Qwen, xAI, OpenRouter and any OpenAI-compatible API are supported).
4. Type one sentence describing your goal and let the AI team work.

If you attach a custom domain, add it to `AO_ALLOWED_HOSTS` (comma-separated).

## Common Use Cases

- Business plans, product specs, marketing strategies and technical designs from a single prompt
- Multi-perspective reviews (tech + design + business) merged into one decision
- Repeatable YAML workflows for content, research and planning, with resumable runs
- Shareable single-file HTML reports of each run for your team

## Dependencies for Agency Orchestrator Hosting

- Docker image `ghcr.io/jnmetacode/agency-orchestrator`
- An API key for at least one LLM provider (entered in the Studio)

### Deployment Dependencies

- Source: https://github.com/jnMetaCode/agency-orchestrator
- English README: https://github.com/jnMetaCode/agency-orchestrator/blob/main/README.en.md

### Implementation Details

The "key-free" providers that reuse locally logged-in coding CLIs (Claude Code, Codex, Copilot…) are meant for desktop use and are not available in this container; use API-key providers instead. Run outputs persist on the `/data` volume.

## Why Deploy Agency Orchestrator on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying Agency Orchestrator on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.


## Similar templates

- [Chat Chat](https://railway.com/deploy/-WWW5r) — Chat Chat, your own unified chat and search to AI platform.
- [Weaviate](https://railway.com/deploy/weaviate-1) — Vector database with hybrid search and an API key-protected API
- [Möbius Personal AI OS](https://railway.com/deploy/mobius-v01-personal-ai-os) — Self-hosted AI agent that builds and runs apps for you, with memory.

Open this page in a browser: https://railway.com/deploy/agency-orchestrator-ai-team