A lightweight WebAssembly runtime that starts in microseconds, runs anywhere from the cloud to the edge, and quietly grew into one of the friendliest places to run portable AI.

Welcome to WasmEdge: A Lightweight WebAssembly Runtime for Cloud, Edge, and AI.

WasmEdge is a CNCF sandbox project that takes WebAssembly — a portable, sandboxed bytecode format born in the browser — and turns it into a serious server-side runtime for cloud-native, edge, and decentralized workloads. It boots a hundred times faster than a Linux container, packs into a fraction of the size, and runs the same compiled module unchanged across CPU architectures and operating systems. Where plain WebAssembly is deliberately walled off from the outside world, WasmEdge adds the capabilities real applications need: filesystem and network access through WASI, an ahead-of-time compiler that produces native-speed code, a plugin system for host functions, and a remarkable AI inference stack that runs large language models and other neural networks through the WASI-NN interface. This book starts with the problem WebAssembly solves on the server, walks through WasmEdge's architecture, its execution modes, the sandbox and the host-function bridge, the WASI extensions for sockets and storage, the AI story built on llama.cpp and friends, the language SDKs for embedding the runtime, the path to running Wasm as ordinary OCI containers under Docker and Kubernetes, and finally how to operate it well and where it fits in the wider ecosystem.

This title is part of the ShriIra library and is free to read in full, right here — our small contribution to making world-class knowledge easy to reach.

A note on reading it: open the Contents menu at the top of the reader to jump between chapters, use the Aa menu to set a comfortable text size, theme (light, sepia, or night), and single- or two-page layout. Your place is saved automatically, so you can always pick up where you left off.

We hope it serves you well.

— Shriira Press

Contents

1. Chapter 1 — Why WasmEdge Exists
2. Chapter 2 — Architecture and the Execution Pipeline
3. Chapter 3 — Running Modules and the AOT Compiler
4. Chapter 4 — The Sandbox and Host Functions
5. Chapter 5 — WASI and the Networking, Storage Extensions
6. Chapter 6 — AI Inference with WASI-NN
7. Chapter 7 — Embedding WasmEdge with Language SDKs
8. Chapter 8 — Wasm as OCI: Docker, containerd, and Kubernetes
9. Chapter 9 — WasmEdge in Practice