kolezka/self-improvement-loop

self-improvement-loop

A Claude Code plugin that learns from your sessions. It reflects on them in the background, promotes recurring lessons into skills, hooks, rules and agents, and tracks whether those artifacts actually get used. Nothing reaches a shared remote without a human.

OpenClaw sessions feed the same loop. See docs/OPENCLAW.md.

Contents

• How the loop works
• Requirements
• Install
• Quick start
• Commands
• How lessons reach a session

• Feedback and scorecards
• Configuration
• Worlds
• Model providers
• Patterns and aliases
• Moving to another host

• Privacy
• Development
• Documentation
• License

How the loop works

flowchart LR
  A[Session hooks record events] --> B[Worker reflects out of session]
  B --> C[Reflections cluster by pattern]
  C -->|3 occurrences| D[Curriculum drafts an artifact on a branch]
  D --> E[Human accepts, rejects, rehomes or retires]
  E --> F[Lesson delivered to the next matching session]
  F --> G[Usage and feedback scorecards]
  G --> D

Hooks record what happened in a session. They are fast, one bundled script, never blocking, and they never call a model. A worker, running on a schedule outside any session, reflects on sessions that ended or went idle: it builds evidence from the transcript, makes one model call, and writes a reflection if there is a real lesson.

Reflections cluster by pattern. Three occurrences of the same pattern trigger curriculum, which drafts and stages an artifact on a branch. You review and accept it (or reject, rehome, retire it) in the web UI or the CLI. Once accepted, the next session that matches gets the lesson delivered as context, and usage of the new artifact starts feeding a scorecard that the next curriculum pass reads.

See docs/ARCHITECTURE.md for the full picture and docs/V1-PARITY.md for what carried over from the previous (dotfiles-next) version of this loop and what changed.

Requirements

| Requirement | Notes | | --- | --- | | bun = 1.4.2 | Runs every part of the plugin: hook fast path, CLI, worker, web UI. | | git | Artifacts are staged on a branch in a target repo. | | A model endpoint | An OpenAI-compatible proxy (LiteLLM, Ollama) or the claude CLI on PATH. |

Install

claude plugin marketplace add kolezka/marketplace
claude plugin install self-improvement-loop@kolezka

See docs/INSTALL.md for local dev installs and running on a schedule.

Quick start