sunnygo

great! have you tested how well it return coordinates of objects/text? Ive tried with generic LLMs like Gemini/Qwen/Gemma and they all are unstable with coordinates around text, better when using visual grounding though

how Mistral OCR works for you? Is it really better than Tesseract?

Made "stop localhost" publishing for vibe coders called Revdoku. It is useful when need to quickly publish a prototype, report, set of documents and can be done right from Claude or Codex.

If you use ChatGPT then can say it is more like ChatGPT Sites but also works in Claude.

noisetable is great, though would be great to have a warning that it uses flickering before starting the game. Or maybe add a check if visitor has motion reduced (prefers-reduced-motion css block?)