BayramAnnakov/claude-reflect

1,049 stars · Last commit 2026-03-16

A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.

README preview

# claude-reflect

[![GitHub stars](https://img.shields.io/github/stars/BayramAnnakov/claude-reflect?style=flat-square)](https://github.com/BayramAnnakov/claude-reflect/stargazers)
[![Version](https://img.shields.io/badge/version-2.6.0-blue?style=flat-square)](https://github.com/BayramAnnakov/claude-reflect/releases)
[![License: MIT](https://img.shields.io/badge/License-MIT-green?style=flat-square)](https://opensource.org/licenses/MIT)
[![Tests](https://img.shields.io/badge/tests-160%20passing-brightgreen?style=flat-square)](https://github.com/BayramAnnakov/claude-reflect/actions)
[![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Linux%20%7C%20Windows-lightgrey?style=flat-square)](https://github.com/BayramAnnakov/claude-reflect#platform-support)

A self-learning system for Claude Code that captures corrections and discovers workflow patterns — turning them into permanent memory and reusable skills.

## What it does

### 1. Learn from Corrections

When you correct Claude ("no, use gpt-5.1 not gpt-5"), it remembers forever.

```
┌─────────────────┐     ┌─────────────────┐     ┌─────────────────┐
│  You correct    │ ──► │  Hook captures  │ ──► │  /reflect adds  │
│  Claude Code    │     │  to queue       │     │  to CLAUDE.md   │

View full repository on GitHub →