Self-evolving skill engine for Claude Code — skills that create, score, repair, and harden themselves through recursive improvement loops

Self-evolving AI assistant starter kit. Markdown-only. Works with Claude Code, Codex, Devin, Cursor, and any LLM agent

Agent Reliability Engineering: applying SRE principles to AI agent systems. Evals, imp@k metrics, self-improvement, config versioning, transfer experiments.

Self-refining AI agents for software development — critique every session, accumulate evidence, and automatically improve their own system prompts. Works with Claude Code & GitHub Copilot.

AI-First Development Methodology v2.0 for Claude Code — spec-driven pipeline with blocking gates, unified triad-based knowledge system, design pipeline, and automated validators. Session-aware, self-improving via quick-learning loop.

SPEAR Framework — Spec, Plan, Execute, Audit, Ratchet. A self-improving AI-driven development methodology.

Self-improving AI pipeline that autonomously discovers, builds, audits, and ships improvements to any codebase. 4 agents, 5 phases, eval gating, continuous learning. Plugin for Claude Code & Gemini CLI.

A self-improving product system that reads reports, identifies priorities, and autonomously implements fixes

Enable AI agents to adapt your voice, track priorities, and evolve through markdown files without relying on APIs or runtime environments.