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

@ruvector/edge-full

Run vector search, graph queries, and ONNX inference in browser environments.

1|Updated Feb 8, 2026
Search Tags:#rag#vector search#wasm#neural networks#graph database#onnx#edge ai
One-click install
npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-edge-full
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: @ruvector/edge-full
Source: https://github.com/ricable/cli-skills-builder/tree/main/.claude/skills/ruvector-edge-full
Command: npx skills add https://github.com/ricable/cli-skills-builder --skill ruvector-edge-full

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a comprehensive toolkit for running advanced AI functionalities like vector search, graph databases, and neural network inference directly in browser or edge environments, eliminating the need for complex server-side setups.

Core Features & Use Cases

  • Vector Search: Efficiently search and retrieve similar data points based on vector embeddings.
  • Graph Database: Query and manage complex relationships between data using Cypher, SPARQL, and SQL.
  • Neural Inference: Run ONNX models for tasks like classification, object detection, and more, directly on the edge.
  • DAG Workflows: Orchestrate complex AI pipelines with a directed acyclic graph scheduler.
  • Use Case: Build a fully offline RAG (Retrieval Augmented Generation) application in the browser that embeds user documents, performs similarity searches, and then uses a local LLM for response generation.

Quick Start

Initialize the EdgeRuntime with desired features and start it.

Frequently Asked Questions about @ruvector/edge-full

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

FAQPage Schema
How do I run a fully offline RAG application in the browser?▼

You can build a fully offline RAG application in the browser by using a WebAssembly-based edge AI runtime to embed documents, perform vector search, and execute local ONNX inference for response generation without server-side setups.

What is WebAssembly edge AI and how does it handle neural networks?▼

WebAssembly edge AI handles neural networks by providing an all-in-one runtime that executes ONNX models directly in browser or edge environments, enabling local inference for tasks like classification and object detection.

Can I query a graph database in the browser using SQL and Cypher?▼

Yes, you can query a graph database in the browser using SQL, Cypher, and SPARQL by leveraging a WebAssembly-based edge AI runtime to manage complex data relationships directly on the client side.

Does WebAssembly edge AI support persistent vector search data?▼

Yes, WebAssembly edge AI supports persistent vector search data by utilizing IndexedDB for local data storage, allowing you to retain vector embeddings and graph relationships directly in the browser environment.

What is the best way to orchestrate complex AI pipelines on edge devices?▼

The best way to orchestrate complex AI pipelines on edge devices is by using a directed acyclic graph (DAG) workflow scheduler within a WebAssembly runtime to coordinate vector search and neural network tasks.

Related Skills

Explore More Software Engineering Skills→
ricablericable
1

ruvector-onnx-embeddings-wasm

Generate text embeddings with ONNX Runtime in WebAssembly.

Community
Intermediate
MassimilianoPiliMassimilianoPili

dba-graphdb

Manage Neo4j 5+ and Apache AGE graph database design and administration tasks.

Community
Advanced
ricablericable
1

@ruvector/edge

Run browser-based AI swarms with P2P networking and vector search.

Community
Advanced
jonnabiojonnabio
6

pinecone

Manage vector databases with hybrid search for AI applications.

Community
Advanced