claude-opus-5-5-demo
A demo repo of three browser 3D games, each generated from a single prompt in one session with no manual code edits. It shows what Claude Opus 5.5 can produce in code generation.
Share on XNo license declared
Overview
This repository holds three playable 3D browser games used to test the code generation of Claude Opus 5.5. Each game came from a single one-sentence prompt in one session, with no manual edits to the code, and each is deployed on Cloudflare Pages. The games are a pelican cycling along a coastal road, a team FPS on a transport ship, and a drifting racing game. Each is a single HTML file, with models, textures and sound generated by code.
Key features
- Three 3D games: pelican cycling, transport ship FPS, racing
- Each built from one one-sentence prompt in one session
- Source code left unedited by hand
- Single-file HTML with procedurally generated assets
- Original prompts and build steps included
Best for
Readers who want to see what one-shot code generation with Claude Opus 5.5 produced, or study the prompts and source. The README is written mainly in Chinese.
- Upstream
- riba2534/claude-opus-5-5-demo
- Fork on GitHub
- Guo-astro/claude-opus-5-5-demo
- Upstream stars
- 881
- Category
- AI agents and LLM tools
- License
- No license declaredWithout a license, the author keeps all rights. Ask the upstream owner before reusing the code.
- Forked
- 2026-09-23
- Sync status
- In syncLast synced 2026-09-29
More in AI agents and LLM tools
A free desktop app where children in non-English-speaking countries practice English speaking and listening by talking with an AI companion. It can run locally and offline.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
An agent skill for Chinese patents. It helps find patentable points, write disclosure documents, explain patents in plain language, follow policy changes and assist with examination replies.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub
A minimal Python library from Hugging Face for building AI agents that write and run code to solve tasks. It lets you set up capable agents in a few lines.
Forked 2026-09-28Last synced 2026-09-29License: Apache-2.0AI agents and LLM toolsGitHub
An open-source benchmark that measures how well AI agents handle realistic legal work. It provides tasks and evaluation for improving legal agents.
Forked 2026-09-28Last synced 2026-09-29License: MITAI agents and LLM toolsGitHub