What do you want to do?
3 use cases
-
Scaffold an AI engineering team into an existing repo
Run init to detect your stack and set up eight specialist roles with evidence gates.
- REPO
rafmacalaba/armada - Software and DevOps
- Intermediate
View prompt
In <repo>, run `armada init`, list the specialist roles it created, and explain which gate each transition requires. Confirm no source files outside the scaffold changed.
- REPO
-
Run two features in parallel without clobbering each other
Boot separate lanes per feature and watch them all from a fleet dashboard.
View prompt
Start armada voyages for <feature A> and <feature B>, monitor with `armada fleet`, and report each lane's status. Confirm each produced its own PR without touching the other's files.
-
Start a new app with an AI team from day one
Use Armada new to answer a questionnaire and get a scaffolded project ready to ship.
- REPO
rafmacalaba/armada - Software and DevOps
- Intermediate
View prompt
Run `npx @rafamacalaba/armada@latest new <app name>`, answer the questionnaire for <stack>, and start one voyage. Report the files created and the first PR's checks.
- REPO
Quick start with Armada
- Check you have what it needs: Node.js and npm; A coding agent and model access (README references OpenRouter pricing).
- Open rafmacalaba/armada on GitHub and read the README and license.
- Install with
npm install -g @rafamacalaba/armada - Run
cd your-repo && armada init - Review the scaffolded roles and contracts
- Start a feature lane
These steps come from our top use case, Scaffold an AI engineering team into an existing repo, which also has a copy-paste agent prompt.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for rafmacalaba/armada
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeAbout this repo
- Who it is forDevelopers who want more structure and verification around AI coding agents than a single unsupervised session.
- Why it is hot104 stars, launched 86 days ago
- LanguageJavaScript
- Sourcegithub.com/rafmacalaba/armada · Back to Hot repos
Requirements
- Node.js and npm
- A coding agent and model access (README references OpenRouter pricing)
Add this badge to your README
Maintain Armada? Show readers where to find these use cases.
Markdown
[](https://dedupedai.com/use-cases/rafmacalaba-armada/?utm_source=github&utm_medium=badge&utm_campaign=rafmacalaba-armada)
HTML
<a href="https://dedupedai.com/use-cases/rafmacalaba-armada/?utm_source=github&utm_medium=badge&utm_campaign=rafmacalaba-armada"><img src="https://dedupedai.com/badge/rafmacalaba/armada.svg" alt="Use cases on Deduped" height="20"></a>
A static image, no tracking script. About the badge
Questions about Armada
What is Armada?
armada is an npm CLI that scaffolds a team of eight AI specialist agents into a repository and runs contract-driven, evidence-gated feature work in parallel lanes that end in pull requests. It is an open-source project on GitHub: https://github.com/rafmacalaba/armada.
How do I use Armada?
Install with npm install -g @rafamacalaba/armada; then run cd your-repo && armada init; review the scaffolded roles and contracts. The use cases on this page give the full steps and a copy-paste agent prompt for each job.
Who is Armada for?
Developers who want more structure and verification around AI coding agents than a single unsupervised session.
What can I do with Armada?
3 use cases so far, for example: Scaffold an AI engineering team into an existing repo; Run two features in parallel without clobbering each other; Start a new app with an AI team from day one. Each has steps and a copy-paste agent prompt.
What do I need to run Armada?
Node.js and npm; A coding agent and model access (README references OpenRouter pricing).
What are alternatives to Armada?
Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.
Is Armada safe to run?
Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.