A library providing TypeScript types and Zod schemas for the sona API
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
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
Complete WASM toolkit for edge AI: vector search, graph DB, neural networks, DAG workflows, SQL/SPARQL/Cypher, and ONNX inference - all running in browser
Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference
Useful libraries for talking to Sonatype services, using javascript
WASM bindings for RuvLLM - browser-compatible LLM inference runtime with WebGPU acceleration
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.
Integration module - agentic-flow@alpha deep integration, ADR-001 compliance, TokenOptimizer
RuVector WASM package bridges for Claude Flow plugins
A set of contracts for the sona protocol
Neural module - SONA learning integration, neural modes
Self-Optimizing Neural Architecture - Runtime-adaptive learning for LLM routers with two-tier LoRA, EWC++, and ReasoningBank
Integration module - agentic-flow@alpha deep integration, ADR-001 compliance, TokenOptimizer
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
AI coding agent for your terminal. Fast, capable, cost-effective.
Integration module - agentic-flow@alpha deep integration, ADR-001 compliance, TokenOptimizer
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
Package contains helpers for easy build and test microservices based on NodeJS & inverted json.
Self-learning LLM runtime — TurboQuant KV-cache (6-8x compression), SONA adaptive learning, FlashAttention, speculative decoding, GGUF inference
Complete WASM toolkit for edge AI: vector search, graph DB, neural networks, DAG workflows, SQL/SPARQL/Cypher, and ONNX inference - all running in browser
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
@eeacms/volto-clms-utils: Volto add-on