skills.rest
ricable
ricableCOMMUNITY
Explore all skills by this author →
GitHub

ruvector-gnn-wasm

Provides WebAssembly-compiled Graph Neural Network inference for browsers and edge devices.

1|Updated Feb 8, 2026
Search Tags:#edge computing#wasm#browser#webassembly#inference#graph neural networks#gnn
One-click install
npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-gnn-wasm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ruvector-gnn-wasm
Source: https://github.com/ricable/cli-skills-builder/tree/main/.claude/skills/ruvector-gnn-wasm
Command: npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-gnn-wasm

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables efficient Graph Neural Network (GNN) inference directly within web browsers and on edge devices, eliminating the need for server-side computation and reducing latency.

Core Features & Use Cases

  • Browser-Native GNNs: Run GNN models like GraphConv, GATLayer, SAGEConv, and GINConv directly in the browser using WebAssembly.
  • Edge Deployment: Deploy GNN models to edge devices for real-time inference without server dependencies.
  • Use Case: Integrate client-side knowledge graph embeddings into a web application or build a real-time recommendation system on an edge device using graph data.

Quick Start

Install the @ruvector/gnn-wasm package using npm.

Frequently Asked Questions about ruvector-gnn-wasm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Graph Neural Network inference in a browser without a backend server?▼

You can run Graph Neural Network inference directly in the browser by compiling graph models to WebAssembly. This eliminates server-side computation and reduces latency, enabling client-side execution for web applications.

Can I deploy GNN models to edge devices for real-time inference?▼

Yes, you can deploy GNN models to edge devices for real-time inference without server dependencies. Using WebAssembly-compiled graph layers allows edge computing environments to process graph data locally with near-native performance.

What Graph Neural Network layers are supported for WebAssembly inference?▼

Supported Graph Neural Network layers include GraphConv, GATLayer, SAGEConv, and GINConv. These layers are compiled to WebAssembly to facilitate browser and edge inference with near-native performance.

Does WebAssembly provide near-native performance for client-side knowledge graph embeddings?▼

WebAssembly provides near-native performance for building client-side knowledge graph embeddings. It accelerates graph learning computations directly within web applications, ensuring efficient local processing of graph data.

How do I add WASM-accelerated graph learning to my web application?▼

You can add WASM-accelerated graph learning to web applications by installing the @ruvector/gnn-wasm package via npm. This integrates WebAssembly-compiled GNN layers for browser-native graph inference.

What is the best way to execute GraphConv and SAGEConv layers locally on edge devices?▼

The best way to execute GraphConv and SAGEConv layers locally is using WebAssembly-compiled graph models. This approach bypasses server dependencies, enabling direct real-time inference on edge devices with optimized performance.

Related Skills

Explore More Software Engineering Skills→
SciMate-AISciMate-AI
1

torchdrug

Build, train, and deploy graph neural network workflows for chemistry and biology.

Official
Advanced
jsagirjsagir
2

graph

Translate natural language queries into SQL for SQLite knowledge graphs.

Community
Intermediate
ricablericable
1

ruvector-ruvllm-wasm

Run WebAssembly LLM inference in browsers with WebGPU acceleration.

Community
Advanced
ricablericable
1

@ruvector/graph-wasm

Run a WebAssembly graph database with Cypher queries in browsers.

Community
Intermediate