Artifacts

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

Template-based builder for Microsoft Intune settings such as BitLocker, update rings, Wi-Fi profiles and firewall rules, with AI help.

Japanese-language generator: describe what you want, pick HTML, CSS, PHP or C and a style, and get commented code.

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

Runs prompts against the language model built into Chrome, downloading it on first use.

Counts tokens for text and image attachments across several Claude models using Anthropic token-counting API and your key.

Try one JavaScript library against OpenAI, Anthropic or Gemini models by picking a provider and pasting a key.

Sends prompts with different structures to OpenAI and shows how many tokens were served from cache.

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

No-code interface for training machine learning models on your own data with Hugging Face AutoTrain.

Playground for trying out Hugging Face Hub API calls from the browser.

Describe an application in plain text and have a Qwen model generate its code for you.