The library exposes two independently consumable components:

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

Ultra-fast MicroLoRA adaptation for WASM - rank-2 LoRA with <100us latency for per-operator learning

Letta Code is a CLI tool for interacting with stateful Letta agents from the terminal.

Fastest 5KB JS implementation of secp256k1 ECDH & ECDSA signatures compliant with RFC6979

Vertex AI client for Node.js

JavaScript SDK and CLI for building JavaScript applications on [Fastly Compute](https://www.fastly.com/products/edge-compute/serverless).

Sigmoid (hyperbolic tangent) kernel

[Hypertune](https://www.hypertune.com/) is the most flexible platform for feature flags, A/B testing, analytics, and app configuration. Built with full end-to-end type safety, Git-style version control and local, synchronous, in-memory flag evaluation. Op

Self-learning vector database for Node.js — hybrid search, Graph RAG, FlashAttention-3, HNSW, 50+ attention mechanisms

[](https://github.com/hexlet/cli/actions) [](https://badge.fury.io/js/%40hexlet%2Fcli)

V3 Hooks System - Event-driven lifecycle hooks with ReasoningBank learning integration

Matrix — Agentic OS for OpenCode. Personalizable, communicating, self-improving, resilient.

Machine learning algorithms.

Node module that contains common functionality needed to appcenter-* modules

This module lets you run python code inside node without spawning new processes

AI Manipulation Defense System (AIMDS) with self-learning, prompt injection detection, and vector search integration

API for learning app

A Education First learning activity

Initial React package scaffold for launching the Learning Agent user experience.