Webassembly Local Processing

Foundry Local runs AI models on-device using ONNX Runtime (CPU/GPU/NPU) to keep data local, offering an OpenAI-compatible API, Python/JS/C#/Rust SDKs, a model hub, and CLI tools for edge and enterprise deployments.

AI Toolbox is a browser-based multimedia toolkit that processes video, audio, images, and documents locally via WebAssembly. Files stay on your device, enabling private editing, conversion, and extraction with no account needed.

local.ai runs language models locally without GPUs. Its Rust backend keeps the binary under 10 MB and performs CPU inference with GGML quantization. A single‑click interface streams responses to a UI, while a model manager tracks, verifies, and resumes downloads.

AI‑powered image editor that runs entirely in the browser, offering smart crop, AI expand, format conversion, lossless compression, watermarking, color adjustment, filter, GIF creation, side‑by‑side comparison, and batch workflow design—all processed locally with WebAssembly for speed and privacy.

VibeClaw.dev is a browser-based OpenClaw runtime for running AI coding agents in sandboxed, in-browser Node.js containers. It features a complete virtual filesystem, multi-agent orchestration, and flexible model support from local WebGPU LLMs to cloud APIs, all exportable for private, reproducible w

meshrefinery.com is a browser-based 3D model repair and conversion tool that runs locally via WebAssembly, fixing open edges and non-manifold geometry to produce watertight, slicer-ready meshes while keeping files on your device.

ODS is an on-premises AI server for PC, Mac, and Linux offering local LLM inference, model management, agents, chat/voice UI, RAG with local document search, image pipelines, integrations (Ollama, ComfyUI, n8n), and operational tooling for private deployments.