workflowstacks
local-ai

argosy-launcher: Launch Games

Sync, install, and launch games on mobile devices with argosy-launcher, a tool for founders and mobile gamers.

From the repo · “A native Android client for RomM for syncing, installing, and launching games on any of your mobile devices”

intermediate⏱ 30 minutes💵 Free (self-hosted)
664 stars+16★ this week57 forksKotlinGuide quality 8/10 · reviewed Jun 29Updated 10/21/2026100% free · open source
What it is

Download, sync, and launch mobile games across your devices with the RomM native Android client.

Real use case example

"A gamer, like Emily, can quickly set up RomM on her Android phone and then on her tablet; she syncs her Pokémon Go progress, installs new games, and launches them in just a few taps, never missing a moment to catch 'em all."

When to use it
  • •You need to manage multiple mobile devices for gaming purposes
  • •You want to sync your games across all your mobile devices
  • •You are looking for a tool to simplify the process of installing and launching games on Android devices
Ready-to-paste prompt
To launch a game, use the `argosy-launcher` app and select the game from the list of installed games, then click the `Launch` button
Heads up: You need to have a RomM server set up and configured to use the argosy-launcher app, as it relies on the RomM server for syncing and installing games
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/argosy-launcher && curl -fsSL https://workflowstacks.com/api/skills/argosy-launcher/claude-skill -o ~/.claude/skills/argosy-launcher/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How argosy-launcher: Launch Games works
Codeflow
Free to inspect

Argosy-launcher: Launch Games is a very large Kotlin project (~599k lines across 2700 code files, plus 586 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, GPL-3.0 license, has a test suite.

Size
Very large codebase
~599k lines · 2700 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Java/JVM
Needs API keys (.env)
Kotlin 74%C 14%C++ 8%Java 3%Python 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    .env.example
    The API keys and settings you must provide
  4. 4
    app/src/main/kotlin/com/nendo/argosy/ui/dualscreen/README.md
    Inside app/ — the main logic begins here
What's in each folder
app/Core code — the actual logic2834 files
docs/Documentation7 files
libretrodroid/Folder1423 files
scripts/Helper scripts16 files
design-system-docs/Folder9 files
testbed/Folder7 files
libs/Folder6 files
gradle/Folder3 files
READMEHas testsDocumentedCI checksGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
rommapp
Language
Kotlin
Category
local-ai
Published
12/6/2025

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/argosy-launcher.svg)](https://workflowstacks.com/skills/argosy-launcher?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Related skills

More local-ai tools founders pair with this one.

local-ai★ 132,005
Run Powerful LLMs Locally with llama.cpp – Fast C++ Inference
Empower your product with on‑device LLM inference using llama.cpp’s efficient C++ engine. Ideal for founders who need privacy, speed, and no cloud costs. 130k+ GitHub stars.
local-ai★ 94,719
Stirling-PDF: Edit PDFs Anywhere
Edit PDFs on any device with Stirling-PDF, a tool for startup founders, backed by 80k+ GitHub stars
local-ai★ 38,207
Run AI Locally with llmfit
Find compatible AI models for your hardware with llmfit, a tool for founders, with 29k+ GitHub stars.
local-ai★ 491
xybrid: Deploy On‑Device AI Apps Quickly for Mobile & Edge
xybrid lets founders ship privacy‑first AI features to iOS, Android and Unity apps using Rust, Swift or Kotlin—ideal for edge and game developers.
local-ai★ 3,198
eidos
A single-file relational spreadsheet for you and your agent.
local-ai★ 1,061
llama.rn brings LLM power to React Native apps – 1.1k+ stars
Integrate llama.cpp’s large-language-model capabilities directly into iOS and Android via React Native—ideal for founders building AI-enhanced mobile experiences.