HN Showcase
Back to browse
GitHub Repository

A Claude Code plugin that makes Claude Code self-improve — learning from your corrections, not just remembering them (also support codex now)

657 starsPython

Claude-smart – Make Claude Code self-improve from every session

by yilu331·May 5, 2026·4 points·3 comments
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemBig Brain

Turns corrections into executable playbooks, not just static memory logs.

Strengths
  • •Distinguishes between passive memory and active learning rules for command execution.
  • •Benchmarks show 2.7x quality improvement over existing claude-mem memory tools.
  • •Persists optimization patterns across different projects and repositories.
Weaknesses
  • •Niche utility limited to the small subset of developers using Claude Code CLI.
  • •Relies entirely on user corrections; no proactive error detection mechanism.
Category
AI/ML
Target Audience

Developers using Claude Code CLI

Similar To

claude-mem · Cursor Rules · Windsurf Cascades

Similar Projects

AI/ML●●Solid

A Claude meta-skill that improves all your skills, including itself

It watches your Claude sessions, captures corrections and repeated flows, and produces structured observation logs plus candidate SKILL.md drafts so your skill library can grow without manual audits. The pragmatic split of writing to the filesystem in Cowork versus producing a handoff doc for the web shows an awareness of platform limits. Clever idea, but the README promises methodology without live examples, metrics, or privacy details, so it's interesting on paper more than battle-tested.

Big BrainNiche Gem
rebelytics
114mo ago