webgpu

JavaScript 3D Library.

Babylon.js is a powerful, beautiful, simple, and open game and rendering engine packed into a friendly JavaScript framework.

High-performance In-browser LLM Inference Engine

A cross-platform, safe, pure-Rust graphics API.

Powerful web graphics runtime built on WebGL, WebGPU, WebXR and glTF

Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

3D Gaussian Splat Editor

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

ML-powered manga translator, written in Rust.

The high-speed OpenGL, OpenCL, OpenAL, OpenXR, GLFW, SDL, Vulkan, Assimp, WebGPU, and DirectX bindings library your mother warned you about.

Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

Cross-Platform, GPU Accelerated Whisper 🏎️

Run local LLMs like llama, deepseek-distill, kokoro and more inside your browser

Chat with AI large language models running natively in your browser. Enjoy private, server-free, seamless AI conversations.

Private local model studio, AI chat, and agent workspace powered by WebGPU and WebLLM.

A no-code 3D playground to explore, design, and interact with Agentic AI systems

Vestige gives AI agents sharp memory: a local-first Rust MCP server that reaches backward through time to find the quiet change, decision, or service that caused today’s failure, not the lookalike.

AgentLLM is a PoC for browser-native autonomous agents