This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend
What I Built
My friends and I often spend more time deciding what to play than actually playing. PlayNext was built for a friend who loves PC gaming but can't pick a game when they sit down to play.
Demo
Code
SwagD15
/
PlayNext
PlayNext is a small website that helps gamers decide what to play next. You pick your mood, how much time you have and the kind of game you want, and a local open-weight AI model (Gemma, running through Ollama) suggests three PC games.
PlayNext 🎮
Stop scrolling. Start playing.
PlayNext is a small website that helps gamers decide what to play next. You pick your mood, how much time you have and the kind of game you want, and a local open-weight AI model (Gemma, running through Ollama) suggests three PC games.
The Problem
My friends and I often spend more time deciding what to play than actually playing. PlayNext was built for a friend who loves PC gaming but can't pick a game when they sit down to play.
The Solution
- Choose how you're feeling: Bored, Relaxed, Competitive or Adventurous.
- Choose your time: 15 minutes, 30 minutes or 1 hour+.
- Choose a genre: Surprise me, Action, Adventure, Puzzle or Multiplayer.
- Get three PC game recommendations, each with a short description and a reason it fits.
The recommendations are generated by the AI model (gemma) each time. They are not hardcoded.
Tech Stack
…How I Built It
i used Gemma 3:270m open-source AI model (open-weight model) through Ollama; first my friends choose there preferences(like Bored, Relaxed, Competitive or Adventurous; time - 15 , 30 minutes; Genre etc.) and script.js reads three choices and builds a prompt, It sends the prompt to Ollama's local API (http://localhost:11434/api/generate) than the Gemma generate the three response in JSON format, The page parses the JSON and shows three game cards.
Why Does Open Innovation Matter?
Anyone can swap in a different model, change the prompt or adapt the project for their own friends.
Top comments (0)