kelnishi 

A Pure C# WebAssembly Interpreter. v0.13 introduces selectable linear-memory storage: ManagedArray (byte[], default, ~2 GiB) or NativePointer (NativeMemory.AllocZeroed, no 2 GiB cap) via... More information

WACS unified WebAssembly toolchain: run, build, aot, inspect, bindgen. v1.3 picks up WACS.Transpiler.Lib v0.7's PersistedAssemblyBuilder migration + RVA-mapped data segments, so `wacs build` produces ~11%... More information

WebAssembly Component Model support for WACS. Provides the WIT IDL parser, component types, canonical ABI lift/lower, component instantiation, and the host binding surface for running .component.wasm modules on... More information

DEPRECATED. This package has been renamed to WACS.WASI.Preview1 (consolidating with WACS.WASI.Preview2 under one namespace prefix). It is now a metapackage that pulls in WACS.WASI.Preview1 transitively.... More information

Tiny shared-vocabulary assembly for WACS host bindings. Defines [WacsImport] (annotates a static method as a wasm import implementation) and WacsHostMemory (lightweight wasm-memory accessor passed into binding... More information

WASI-NN host bindings for WACS — wasi:nn@0.2.0-rc-2024-10-28 (component-model WIT) plus the legacy wasi_ephemeral_nn (WITX) ABI. Backend-agnostic core; pluggable backends (ML.NET, ONNX Runtime, ONNX Runtime... More information

Library API for WACS.Transpiler — programmatic ahead-of-time WebAssembly-to-.NET IL transpilation, plus seamless loading of saved transpiled assemblies. v0.7.2 fixes a re-instantiation bug where Module classes... More information

Microsoft.Extensions.DependencyInjection extension methods for WACS.WASI.Preview2. Registers default host implementations + bindings + a pre-wired Linker.

WASI Preview 2 (component-model) host implementations for WACS

AOT-safe binary parser for WebAssembly Component Model `.component.wasm` files — pure byte walker producing a typed ComponentModule, no reflection. Split from WACS.ComponentModel so harness / runtime consumers... More information

Ahead-of-time WebAssembly-to-.NET IL transpiler for WACS. Installs the `wasm-transpile` CLI tool. For programmatic use, reference WACS.Transpiler.Lib.

WASI Preview 1 implementation for WACS. Successor to the deprecated WACS.WASIp1 package; identical API under the new Wacs.WASI.Preview1 namespace. C# `TypeForwardedTo` cannot bridge a namespace rename, so the... More information

OpenVINO backend for WACS.WASI.NN. Implements IBackend for graph-encoding.openvino via the OpenVINO.CSharp.API NuGet. Loads OpenVINO IR (xml + bin) from the wasi-nn multi-builder shape. Ships as a sibling NuGet... More information

ONNX Runtime backend for WACS.WASI.NN. Implements IBackend for graph-encoding.onnx via Microsoft.ML.OnnxRuntime. Ships as a sibling NuGet so consumers wiring only one backend don't pull the OnnxRuntime native... More information

WASI Preview 3 (component-model async ABI) host implementations for WACS. Pinned to wasi-0.3.0-rc-2026-03-15. Vertical-slice v0: wasi:cli/run + wasi:cli/{stdin,stdout,stderr} + the stream<u8> bridge to host... More information

Microsoft.Extensions.DependencyInjection extension methods for WACS.WASI.Preview3. Registers default host implementations + a pre-wired host suite.

ML.NET backend for WACS.WASI.NN. Hosts ONNX inference under an MLContext lifecycle so embedders can compose wasi-nn inference with the rest of their ML.NET pipeline (preprocessing transformers, custom... More information

Microsoft.Extensions.DependencyInjection extension methods for WACS.WASI.NN. Registers the WasiNNBundle that the transpiler's HostPackageResolver direct-links wasi:nn imports against — symmetric with... More information

LlamaSharp / llama.cpp backend for WACS.WASI.NN. Implements GraphEncoding.ggml on the WasmEdge convention (load-by-name plus U8 tensors carrying UTF-8 prompt and response text). Models are resolved by name... More information

TorchSharp / libtorch backend for WACS.WASI.NN. Implements GraphEncoding.PyTorch — load TorchScript modules from byte buffers (graph.load) or by name (graph.load-by-name), run inference through libtorch's C++... More information