Artifacts

Generates code and small apps from a prompt with a choice of models; sign in with Hugging Face.

Generates a web application from a text prompt through vibe coding.

Converts a Hugging Face model to a quantized GGUF file and uploads it to your account; needs login.

Generates a small web app from a prompt and shows the result immediately.

Upload a screenshot of a web page and get HTML that approximates it.

Converts a Hugging Face model to the ONNX format.

Describe a web page or small app and Qwen3-Coder writes the HTML, with a live preview.

Describe a small app and get generated code that previews in the page.

Converts PyTorch model weights to the safetensors format; asks for a Hugging Face token.

Generate and complete code by typing a prompt into the Code Llama playground.

Edit a Jinja chat template and preview how it formats a conversation into model input text.

Converts a Hugging Face model to Apple MLX format and uploads it to your account; needs login.

Converts a sketch or figure image into TikZ code for LaTeX documents.

Scans a repository for bugs using GLM models.

Exports a Hugging Face model to ONNX and opens a pull request with the result; needs login.

Fetches a GitHub repository and merges its files into one text file for pasting into an LLM.

Counts the number of tokens a piece of text uses with the Llama tokenizer.

Writes a GitHub issue draft with SmolLM2 running locally in the browser on WebGPU.

Generate structured output such as JSON from an in-browser WebLLM model.

Vector search over documents using a Postgres running in WebAssembly (PGlite) inside the browser.

Runs a small coding agent entirely in the browser using WebGPU, with no server needed for the model.

Lets you try different tokenizers on your text and compare how each one splits it into tokens.

Searches the web and extracts page content in a form suited to feeding into LLMs.

Browser-based AI assistant that helps write software.