Add 61 kid-friendly mini-games to an app
Two users had Replit Agent autonomously add 61 child-friendly, ad-free mini-games to their game vault, growing it from 40 to 101.
Done withReplit Agent
- What they did
- Users pointed Replit Agent at their existing 40-game mini-games app and told it to reach 101 total games, with one rule only: no repeated games. The agent had full autonomy to choose, build, and integrate the rest. It added 61 new child-friendly, ad-free mini-games on its own.
- How it went
- The vault reached 101 games. The agent generated content faster than the users could playtest every level, so technically working games sometimes lacked engaging design.
- Worth knowing
- Manual playtesting of 200-level or 400-procedural-level games is the main remaining bottleneck.
Try it yourself with Replit Agent
I have a game collection app called [app name] with [current number] games. Add [number] new kid-friendly mini-games for ages [age range]: no ads, no in-app purchases, no violence, and no external links. Build them one at a time, test that each one loads and plays, and stop when they are all in the collection and listed on the home screen with a short description.
Source: X · Sep 13, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
Build a searchable map of funded companies
A software engineer had Replit Agent build a searchable map of Wefunder brick-and-mortar companies in about 3 hours for about $22.
Build a clinic app with booking and trackers
A doctor with no coding experience used Replit to build a clinic app in 5 days with booking integration, prescription requests, health trackers and an AI symptom checker.
Build an AI to-do list web app in 9 hours with Replit Agent
The poster used Replit Agent V2 to build a fully functional AI to-do list web app in about nine hours.
Play RollerCoaster Tycoon
Ramp Labs put Claude Code in RollerCoaster Tycoon.
Play Doom with computer-use agents as an informal benchmark
The OpenClaw team used computer-use agents to play Doom on remote machines, treating game performance as an informal way to improve the computer-use workflow.
Play a button-clicking game via a browser agent
A developer wired Gemini's Computer Use model to Playwright in Java and had it play a simple button-clicking game to verify click-coordinate scaling.