A library to implement reinforcment learning in the easiest way possible.

Self-Optimizing Neural Architecture (SONA) - Runtime-adaptive learning with LoRA, EWC++, and ReasoningBank for LLM routers and AI systems. Sub-millisecond learning overhead, WASM and Node.js support.

Self-learning vector memory for AI agents — single-file .rvf cognitive container with HNSW search, episodic Reflexion memory, causal graph + Cypher, 9 RL algorithms, Thompson Sampling bandit, 41 MCP tools, hybrid (BM25 + dense) retrieval, GNN attention. 1

Build cross platform desktop apps with JavaScript, HTML, and CSS

A factory for kernel functions

Web Assembly streaming Opus decoder with Machine Learning enhancements

Generic build of Mozilla's PDF.js library.

various machine learning routines for node

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

TensorFlow layers API in JavaScript

List of ML tasks for huggingface.co/tasks

Sigmoid (hyperbolic tangent) kernel

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

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

AWS SDK for JavaScript Machine Learning Client for Node.js, Browser and React Native

Provides a smooth, zoomable user interface for HTML/Javascript.

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

Codex CLI integration for Ruflo (claude-flow) - OpenAI Codex platform adapter

Reusable React components for Instant Learning.

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