A developer has built a privacy-first drug interaction checker that runs entirely in the browser using WebGPU and WebLLM, eliminating the need to send sensitive medical data to remote servers. The too…
SwarmLLM, an open-source project by developer Nehanth, enables a Qwen 3.8 27B model to run across browser tabs on multiple devices, with each device holding a slice of the model and passing 10 KB acti…
A developer's browser-side image compressor, built with Rust compiled to WASM and WebGPU, crashed for every format after enabling cross-origin isolation in production. The root cause was that the thre…
Martin Delophy is building Timeline Studio, an open-source, local-first video editor that runs in the browser, aiming to determine whether browsers can support serious media workflows. The project rel…
Ben Houston's Three-LLM library runs LLMs entirely in the browser via Three.js and WebGPU, supporting GPT-2, Llama-style, Gemma 3, Phi, and Qwen3.5 architectures, with checkpoints from 3M to 1.3B para…
WebLLM, an open-source library from MLC AI, enables running large language models like Llama 3, Mistral, and Phi-3 directly in the browser via WebGPU, eliminating server-side latency and data privacy …
A developer built a hybrid video upscaler that runs entirely in the browser, dynamically switching between AI-based ONNX inference and WebGPU spatial upscaling based on input resolution. The tool, par…
An emerging architecture enables large language models to run directly in web browsers via WebGPU, shifting inference from cloud servers to user devices. The open-source WebLLM engine provides an Open…
Hugging Face released @huggingface/kernels, a JavaScript library for loading and running optimized WebGPU kernels from the Hugging Face Hub, along with an initial collection of 207 kernels published a…
A developer outlines a blueprint for building a full-stack AI creative studio using Next.js, WebGPU, Node.js, and TypeScript. The architecture leverages a distributed, hybrid model with client-side ha…
Google's LiteRT.js, a browser runtime for on-device AI inference using WebAssembly and WebGPU, enables developers to run standard .tflite models directly in the browser, as demonstrated in a tutorial …
A developer built Apogee, an open-source browser extension that summarizes and answers questions about webpages, PDFs, DOCX files, videos, emails, and text using local AI models. The extension runs en…
A developer detailed how to rate-limit and secure generative AI media pipelines, which are vulnerable to resource exhaustion and denial-of-service attacks due to their non-linear compute costs. The ap…
Running an LLM in a browser tab without an API key or cloud bill is now possible, but users must verify the model file, browser exposure, and data leakage before trusting it with private documents. We…
LerSent001 released Liquid Orb Editor, a real-time liquid glass orb editor built with React, WebGPU/WGSL, and Toolcraft UI, offering 12 editable dynamic sphere presets, parameter controls for color, s…
An engineer detailed the architectural challenges of building credit and compute billing systems for GPU-heavy visual workflow engines, proposing a unified currency called Granular Compute Units (GCUs…
Vercel has open-sourced vgpu, a TypeScript WebGPU library for AI agent shaders, under an MIT license and published to npm at v0.3.1. The library treats .wgsl files as importable modules, runs the same…
Roderick Green released circuit-eval, an MIT-licensed open-source project that uses hardware synthesis and bitslicing to generate fast poker hand evaluators for Texas Holdem and Omaha, claiming the Om…
A developer built MysteryMist, a detective game that runs entirely in the browser using WebGPU to power a private on-device AI. The game's narrative engine operates offline, with no data leaving the d…
Developer Matt DesLauriers released WindFoil, an algorithm for filling 2D vector shapes with per-pixel winding and analytic anti-aliasing in a fragment shader, designed to improve on the Slug Algorith…