Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear

Library implementing the q-learning algorithm and several exploration algorithms.

Library implementing the double-q-learning algorithm.

Reinforcement learning (Q-Learning) library

Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear

A tabular implementation of the SARSA reinforcement learning algorithm which is related to Q-learning

The Reinforcement Learning with Deep Q-Networks (DQN) is a Python class that implements the DQN algorithm for reinforcement learning tasks. It allows agents to learn optimal policies through interaction with an environment using Q-learning and deep neural

Self-Optimizing Neural Architecture (SONA) for Cognition — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual learni

A fast fifo implementation similar to the one powering nextTick in Node.js core

A lightweight Reinforcement Learning engine for NPM usage, built with Q-learning logic.

TypeScript definitions for q

A comprehensive library for mime-type mapping

Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear

swc integration for jest

Image Quantization Library in **TypeScript** *(MIT Licensed)*

Compute the euclidean distance between two vectors

Encode and decode quoted printable and base64 strings

asynchronous function queue with adjustable concurrency

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.

Hooks for managing, caching and syncing asynchronous and remote data in React