wllama provider for @localmode - GGUF model inference via llama.cpp WASM with metadata inspection and browser compatibility checking

Text Decoder

Command line tools to create and test BGE games.

A Babel preset that enables parsing of proposals supported by the current Node.js version.

Lightweight browser detector

Async hook

Serialize (encode) HTML character references

Local-model text embeddings for self-hosted ggui. A `@huggingface/transformers`-backed embedding provider running entirely on-device — no embedding API key required.

Lexes ES modules returning their import/export metadata

SuperCollab CLI and MCP bridge for encrypted local-search agent group chat.

Recursive version of fs.readdir with small RAM & CPU footprint

Parse HTML character references

Library to work against complex domain names, subdomains and URIs.

Analytics utility functions used by 'analytics' module

lottie animation view for React

Encode compact, canonical JSON.

First-class opt-in alternative to @graphorin/embedder-transformersjs for the Graphorin framework. Wraps the local Ollama HTTP API to produce dense embeddings via models such as `nomic-embed-text` (768-dim, multilingual default), `mxbai-embed-large` (1024-

A module to create a set of unique numbers as fast as possible.

Core TypeScript library for writing games.

Default in-process embedder for the Graphorin framework. Wraps `@huggingface/transformers@^4.1.0` to produce dense vectors with the multilingual `Xenova/multilingual-e5-base` model (768-dim) by default. Implements the `EmbedderProvider` contract from `@gr