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
[](https://github.com/BayramAnnakov/claude-reflect/stargazers)
[](https://github.com/BayramAnnakov/claude-reflect/releases)
[](https://opensource.org/licenses/MIT)
[](https://github.com/BayramAnnakov/claude-reflect/actions)
[](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 │