Imagerry, a freemium 100% client-side image converter and utility suite, has launched on Hacker News. The tool processes all conversions locally using HTML5 Canvas and WebAssembly, supporting formats …
SlopSift is a local, graph-backed linter for AI writing that uses a custom-trained dependency parser to detect canned arguments, unsupported claims, and filler. The tool runs quantized ONNX weights lo…
Puter released a demo of Firefox running in WebAssembly inside a Chrome browser, using an estimated $25,000 in Claude Opus and Fable tokens under a Claude Max subscription plan. The project compiles t…
Simon Willison released a new version of his Mermaid to ASCII art tool, compiled from the AlexanderGrooff/mermaid-ascii Go library to WebAssembly, adding color support. The tool, available at tools.si…
ONNX v1.22.0, published June 30, introduces Opset 27 with LinearAttention and CausalConvWithState operators that enable modern hybrid LLMs to export cleanly to ONNX for the first time, alongside WebAs…
Google released LiteRT.js on July 9, 2026, a JavaScript binding of LiteRT that runs .tflite models in browsers via WebAssembly, XNNPACK on CPU, ML Drift over WebGPU, and experimental WebNN for NPUs. G…
Developer Eli Bendersky reports that using LLM agents to build a new Go project from scratch, watgo, was a productivity gain but required extensive human review and refactoring, contrary to hype about…
A developer built a semantic search engine that runs entirely in the browser using a static embedding model (model2vec) instead of a full transformer, reducing the model size to a 4 MB lookup table. T…
A developer has built LOOM, an open-source language that acts as a trust layer for AI-written code by proving safety before execution. LOOM now includes memory safety checks, increasing its self-verif…
Researchers introduced Auto, a compiler that converts LLM agent behavior into verified, low-cost programs, achieving 96.9% parity on witnessed inputs at 6.4x lower cost on the AUTO-BENCH benchmark. Th…
OCR Buddy, a free and open-source Chrome extension, provides fully local OCR for code, formulas, and tables using PaddleOCR's PP-OCRv5 on ONNX Runtime Web, ensuring no data leaves the user's machine a…
A developer built Cutout, an AI background remover that runs entirely in the browser using WebAssembly and WebGPU, ensuring no photos are uploaded to any server. The tool offers instant removal, batch…
Pixlane Media has built a suite of browser-based image, PDF, and AI tools using WebAssembly and on-device processing, eliminating the need for file uploads to servers. The platform prioritizes privacy…
Ternlight, a 7 MB embedding model using ternary quantization and WebAssembly, enables fully client-side semantic search in browsers, bypassing server round-trips and API costs. The model runs locally …
WebAssembly (WASM) and the Ternlight framework enable compact, high-performance AI deployment for low-bandwidth areas. The approach uses model compression, WASM conversion, and offline operation to de…
NoiseLang, a programming language where every value is a probability distribution, has been revived after nine years using AI tools. The language compiles to a JIT runtime via Cranelift and a WASM bac…
A developer conducted three toy projects with different AI usage rules: hand-building a WASM language, having AI write a Prolog implementation in WAT assembly, and having AI reimplement a PalmPilot ap…
Srinivas Thalada launched Much, a local-first AI workspace featuring an in-browser Python sandbox powered by WebAssembly, enabling users to run AI models and code securely on their own devices.…
AetherCut implements hardware-accelerated video editing entirely in the browser, using WebGL for real-time chroma key compositing and WebAssembly to run OpenAI's Whisper model locally for offline tran…
Moss, a sub-10 ms semantic search runtime, removes the need for a vector database in AI agent stacks by embedding search and embedding inside the application process, eliminating network hops. Benchma…