Shipped default skills (continuity, learning-loop, dream) and builtin slash commands

Self-Improving 4-Phase Development Orchestration System for Claude Code - Evolves through meta-analysis learning loop with experimentally validated 20-44% efficiency gains

Pi extension that adds a trajectory-based self-learning loop — automatic capture, reflection, and contextual injection of learnings.

LLM agent + LLM-as-Judge + Human-in-the-Loop review + learning loop, as an embeddable library

SDLC-specific orchestration for the [Substrate](https://github.com/johnplanow/substrate) platform. This package contains the phase-aware handlers, graph orchestrator, DOT pipeline topology, verification pipeline, learning loop, and unified run manifest th

Yuanxi — a cross-agent learning-loop skill: captures mistakes, corrections and insights as reusable .learnings/ entries for later sessions and skill improvement. Triggers on command failure / user correction / a better approach / a missing capability / an

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

A threshold is a value plus the authority that set it, the subject it reaches and the reason it exists. The precedence lattice, the rule → config → constant read with its fallback journalled once per boot, the learning loop, the generated policy prose, an

Local ATI math learning loop for printable practice, PDF grading, and mastery tracking.

BrainAgent — brain-inspired plugin for DeepSeek Harness (dsh): a pipeline of heuristic filters, statistical memory stores and context injections; reward-ledger + UCB1 bandit learning loop (RL-lite)

Governed adaptation kernel: evidence, inert candidates, independent review, exact activation, measured outcomes

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

The default learning-loop reflector: watches finished turns and proposes memory/skill improvements as a one-time nudge on the next provider call — never a silent write. The model may act via memory_save/synthesize_skill, which still hit their own permissi

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

A shim for the setImmediate efficient script yielding API

AI-powered meeting analysis & document generation CLI — video + document processing, deep dive docs, dynamic mode, interactive CLI with model selection, confidence scoring, learning loop, git progress tracking

A self-calibrating terminal coding agent that learns your repo — Bun + Ink, with MCP, sub-agents, background tasks, and an evidence-gated learning loop

Self-organizing multi-agent swarm for Kiro CLI. Adaptive model routing across the real 19-model catalog, evidence-based escalation, and a learning loop that gets cheaper over time. One install, zero config.

High-priority task queue for Node.js and browsers

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