UditAkhourii/adhd

661 stars · Last commit 2026-05-30

ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. The no-brainer skill for creative and interdisciplinary work.

README preview

<p align="center">
  <a href="https://adhdstack.github.io/">
    <img src="docs/hero.png" alt="ADHD for Claude Code" width="100%">
  </a>
</p>

# ADHD — a skill for agents

[![CI](https://github.com/UditAkhourii/adhd/actions/workflows/ci.yml/badge.svg)](https://github.com/UditAkhourii/adhd/actions/workflows/ci.yml)
[![npm](https://img.shields.io/npm/v/adhd-agent.svg)](https://www.npmjs.com/package/adhd-agent)
[![license](https://img.shields.io/badge/license-MIT-blue.svg)](./LICENSE)
[![Node](https://img.shields.io/badge/node-%3E%3D18-brightgreen)](./documentation/install.md)
[![Paper](https://img.shields.io/badge/paper-preprint-blueviolet)](https://adhdstack.github.io/)
[![Featured: The New Stack](https://img.shields.io/badge/featured-The%20New%20Stack-ff5500)](https://thenewstack.io/claude-code-adhd/)

> **An architectural fix for premature convergence in autoregressive reasoning.**

Linear Chain-of-Thought anchors on whatever it says first. Tree-of-Thought widens the search but still walks a single shared context, so the anchoring persists across branches. **ADHD treats this as an architectural problem, not a prompting one** — it spawns N isolated reasoning processes under deliberately distorted cognitive frames, with zero shared context during divergence, then runs a separate critic pass to score, cluster, prune traps, and deepen the survivors.

Reach for it on **design decisions, fuzzy debugging, naming, API surface design, strategy, and any prompt of the shape *"give me a few ways to…"***.

View full repository on GitHub →