Node.js Streams, a user-land copy of the stream library from Node.js
TypeScript port of SYSTRAN/faster-whisper for Node.js, built on CTranslate2, Koffi, FFmpeg, and ONNX Runtime.
React Native binding of llama.cpp
TypeScript declaration files for deck.gl
Structural prompt firewall for LLM apps. DOMPurify philosophy applied to prompt injection & jailbreak defense — deterministic, honest about its limits.
WebGPU worker runtime with a lock-free job queue for WGSL workloads.
An animation library for JavaScript and React.
Advanced lighting WGSL modules and planning profiles for @plasius/gpu-worker.
Knowledge base CLI for AI agents
BSD licensed community fork of mapbox-gl, a WebGL interactive maps library
Modal SDK for JavaScript/TypeScript
Device-negotiated GPU performance governor and quality ladder coordination for Plasius rendering stacks.
Project-scoped memory layer for Claude Code, Codex, Hermes, MCP, and dashboards
Voice Activity Detection (VAD) backends for browsers and Node.js.
Shared browser-safe demo runtime and asset helpers for the Plasius gpu-* package family.
Determine if the current node version supports the `--preserve-symlinks` flag.
A light-weight module that brings Fetch API to node.js
Node.js API (Node-API)
EXPERIMENTAL - USE WITH CAUTION - Launch latest Edge with the Devtools Protocol port open
HyperLite native binary for Linux x64 — terminal-native local AI with CUDA GPU acceleration via Ollama
Node.js binding of ONNXRuntime
Run Hugging Face onnx-community models locally inside pi: registers a chat provider for ONNX text-generation models and a set of tools (embeddings, classification, ASR) backed by @huggingface/transformers and onnxruntime-node.
Text to Speech (TTS) addon for qvac (ggml backend, wrapping the chatterbox + supertonic engines from tts-cpp)
Guten OCR is a high accurate text detection (OCR) Javascript/Typescript library that runs on Node.js, Browser, React Native and C++. Based on PaddleOCR and ONNX runtime