Everything in the catalog

A toolbox of 152 free browser-based tools, available in 17 languages with no signup.

Estimates how much GPU memory a language model needs for a given size, quantisation and context length.

Streams live microphone audio through Whisper on the GPU in your browser and prints the words as you speak.

Transcribes a recording in the browser and labels which speaker said each segment.

Runs a Gemma 4 model in the browser with custom WebGPU kernels, so chat needs no server.

WebGPU-accelerated Whisper that turns microphone or file audio into text locally in the browser.

Speech recognition with the smaller Distil-Whisper model, executed locally in the browser.

Recipe keeper that turns a pasted link into a clean card of ingredients and steps, stored locally with no account.

Converts a document page image into structured Docling markup using a 258M model run in the browser.

Points your webcam at a scene and has a small vision-language model describe it continuously, locally on WebGPU.

Pulls a color palette from an image using WebAssembly and Rust in the browser.

Browser QR generator that overlays a logo, adds UTM campaign parameters and exports PNG or SVG up to 1200 px.

Chat playground that downloads open models and runs them locally on WebGPU with WebLLM.

Datasette running in the browser through WebAssembly to explore SQLite and CSV files.

Markdown editor web app that edits local files through the File System Access API, with optional in-browser AI.

Runs Phi-1 and Phi-2 text generation in WebAssembly through Rust Candle with no server.

Solves sudoku from a camera or uploaded photo, running recognition in the browser.

Runs the llama2.c small Llama model in WebAssembly with Rust Candle, generating text in the page.

Browser-based 2FA code generator offered as an alternative to authenticator phone apps.

Click points on an image and get object masks from Segment Anything running in the browser.

Frontend-only speedcubing timer with scrambles and solve statistics, no server required.

Open-weight text-to-speech that downloads the model once and runs in your browser.

Local-first PWA that combines habit tracking, tasks, finance, journaling and workout logs in one place.

Runs Microsoft's Florence-2 vision model in the browser for captioning, detection and OCR tasks.