SONA Linux x64 GNU native binding

Web Audio API wrapper

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 LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

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 library providing TypeScript types and Zod schemas for the sona API

Neural coordination plugin for multi-agent swarm intelligence using SONA, GNN, and attention mechanisms

Neural module - SONA learning integration, neural modes

A set of contracts for the sona protocol

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.

Open-source protocol definitions for Sona attested transactions

Neural coordination plugin for multi-agent swarm intelligence using SONA, GNN, and attention mechanisms

No description provided.

Protocol toolkit for Sona attested Solana transaction builders

No description provided.

An npm module for creating and publishing Sona extensions.

`sona-cli` is a simple and efficient CLI tool designed to streamline project creation, cache management, and tool upgrades. Built with [Bun](https://bun.sh), it offers a fast and modern JavaScript runtime experience.

Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference

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

Self-Optimizing Neural Architecture - Runtime-adaptive learning for LLM routers with two-tier LoRA, EWC++, and ReasoningBank