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

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-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

TypeScript SDK primitives for the Primer adaptive learning runtime.

Implementation-grounded adaptive learning skills for Codex and Claude Code.

MCP server for Graspful — create adaptive learning courses from AI agents

Create adaptive learning courses from YAML. CLI and MCP server for AI agents.

TypeScript library for building AI agents with cognitive capabilities — perception, memory, reasoning, emotions, and adaptive learning

TypeScript-native cognitive core for adaptive learning and abstraction

AI-powered adaptive learning ecosystem manager - Learn in your unique way

Local-first Claude Agent workbench for education — an adaptive learning loop that diagnoses, teaches, and verifies / 本地优先的 Claude Agent 教育工作台

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

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.

OmniLearn — AI-powered adaptive learning workflow for OpenCode. Multi-agent orchestration that creates personalized roadmaps, hands-on assignments, and tracks progress across any skill.

Adaptive learning curriculum routing algorithm combining FSRS spaced repetition with progress interference decay

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

libraries for dmitrof's adaptive learning system

Adaptive learning layer for Claude Code — skills, agents, teams, and chipsets

MCP server engine for the vibe-hero adaptive-learning plugin — not used standalone; install the vibe-hero Claude Code plugin, which launches this and ships the skills + hook.

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