Deploy and Host Agency Orchestrator AI Team on Railway

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:

Copy AO_WEB_TOKEN from the service's Variables tab.
Open https://YOUR-RAILWAY-DOMAIN/?token=YOUR_TOKEN once — the token is stored in that browser tab and removed from the address bar.
Add an LLM provider in Providers (DeepSeek recommended; OpenAI, Claude, Gemini, Kimi, GLM, Qwen, xAI, OpenRouter and any OpenAI-compatible API are supported).
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.