ursalfas11

Self Improving Brain — AI skill for Claude Code

AI community

Self-improving memory for AI coding agents – Claude Code, Codex, Gemini CLI, Cursor.

How to install Self Improving Brain

This entry records only its repository, not the path inside it, so there is no exact command to give. Open ursalfas11/self-improving-brain and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Self Improving Brain does

Self-improving memory for AI coding agents – Claude Code, Codex, Gemini CLI, Cursor. A local second brain that learns from your corrections. No server.

Alternatives in AI

  • Iai Personal Memory Engine — A cyber brain for your AI 866 ★
  • Wax — Shared Single-file memory layer for all your agents, sub mili-second RAG over text, photo and video on Apple S 791 ★
  • Memory Forge Rs — Stop resetting satisfying AI chats — edit the memory instead 474 ★

README

self-improving-brain: your coding agent forgets everything between sessions. This brain gets smarter with every one.

The self-improving memory & second brain for AI coding agents

It turns your corrections into rules, injects the right rule at the right moment,
and measures whether your agent actually makes fewer mistakes, week after week.

CI Python 3.9+ Zero dependencies No server MIT license GitHub stars

Quickstart · How it gets smarter · Lessons · Agents · Architecture


Demo: on Tuesday the user corrects the agent; that night brain learn turns it into a lesson; on Friday the lesson fires before the agent repeats the mistake

🤯 The problem

You told your agent *"no, don't paper over flaky tests with retries"* last Tuesday. Today it adds a retry again.

Agent mistakes rarely come from missing facts. They come from a rule the agent *knew* but didn't apply **at the moment it mattered**. This bra