DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to have Jevry play and win a 2048 game with Jevry

Ask Jevry to play a supported numeric puzzle game in the browser and report the final board state.

  • Research
  • Intermediate
  • 45 minutes
  • From the README
  • Any agent

Who it is forA hobbyist who wants to watch an agent play a browser game and check its moves on screen.

The problemPlaying a puzzle game through to a win takes time, and watching an agent solve it is a useful test of how it handles page state.

The outcomeThe game reaches a winning tile, with the score and move count reported from the visible page.

What you need first

  • Node.js 22.12 or newer with npm
  • A TypeSafe Jev API key from the official quickstart
  • A separate text-model connection: a locally authenticated Codex or Claude Code CLI, or an OpenAI-compatible or Anthropic API key
  • Budget for model usage, which can cost money and has no fixed per-task cost

Steps

  1. Run git clone https://github.com/michaelswissa/jevry.git and then cd jevry.
  2. Run npm ci, then run npm run dev.
  3. Connect your TypeSafe Jev key and select a text-provider and model that supports image input.
  4. Open a 2048 page and ask Jevry to play and win it, then watch the action feed until the game reports a result.

Prompt for your agent

Use the repo michaelswissa/jevry: run npm run dev, then ask the desktop app to play and win the 2048 game at <game-url>. Expect a win message with a score and move count; verify the win state appears on the visible game board.

Caveat. The README's 2048 victory is a recorded run from an earlier interface, so a new run may not match it and the game may need a vision-capable model.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page