node-llamacpp native backend for AI Matey

In-process GGUF execution adapter for the Graphorin framework. Wraps node-llama-cpp@^3.5 to load .gguf model files directly into the same Node process - no daemon, no port to manage, no GPU contention with other processes. Declares trust: 'loopback' perma

Shared bare addon hosting the qvac-fabric (forked llama.cpp + ggml) runtime for QVAC inference addons

llama addon for qvac

bert addon for qvac

A JavaScript library for Retrieval-Augmented Generation (RAG) within the QVAC ecosystem. Build powerful, context-aware AI applications with seamless document ingestion, vector search, and LLM integration.

Bare-targeted slim assembly of the QVAC SDK. Consumers install only the addon packages they need and register plugins explicitly. No addon dependencies pulled in by default.

The repo is for one of the backend: [llama.cpp](https://github.com/ggerganov/llama.cpp)

llama.cpp LLM Provider

OpenAI-compatible HTTP client for an external or embedded llama-server

RunAnywhere Electron SDK — LlamaCPP backend plugin (LLM / VLM / GGUF embeddings)

MemberJunction Wrapper for llama.cpp - Local Inference via llama-server

WebAssembly binding for llama.cpp - Enabling on-browser LLM inference

LlamaCpp backend for RunAnywhere React Native SDK - GGUF model support for on-device LLM

RunAnywhere Web SDK - LlamaCpp backend for on-device LLM, embeddings, and VLM inference

Node.js Streams, a user-land copy of the stream library from Node.js

A light-weight module that brings Fetch API to node.js

Node.js API (Node-API)

Determine if the current node version supports the `--preserve-symlinks` flag.

A terminal coding agent optimised for **open weights** and local inference. Point it at llama.cpp or Ollama and the whole loop runs on your own hardware: no key, no account, no cloud. Nothing is written to disk without your approval. Cloud providers work