隐私与广告选择

Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载,只有在你同意后,Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策

LogoGit-Stars
星数最高飙升榜AI Agent每日推荐爆款仓库洞察
LogoGit-Stars

用真实 GitHub 数据发现高价值开源项目

GitHub
Built withLogo of Git-StarsGit-Stars
排行榜
  • 星数最高
  • 飙升榜
  • AI Agent
  • 每日推荐
  • 搜索
资源
  • 洞察
  • 编辑政策
关于
  • 关于
  • 联系我们
法律
  • 隐私政策
  • 服务条款
© 2026 Git-Stars. All Rights Reserved.
AD

UditAkhourii/adhd

AI Agent

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.

2.9k 星标219 复刻14 未解决 Issue2.9k 关注者TypeScriptMIT
AI AgentLLM ToolDeveloper ToolUI Framework
评测成熟度

这个仓库详情页已经具备足够的原创分析、来源证据和同类对比,可以作为 Git-Stars 的可索引评测页。

100

评测分

可索引评测
决策摘要

解决的问题

ADHD solves the problem of premature convergence in linear Chain-of-Thought reasoning, where the model anchors on its first output. Unlike standard Tree-of-Thought, it spawns isolated reasoning processes with zero shared context during divergence, then uses a separate critic pass to score, cluster, prune traps, and deepen survivors, enabling more creative and diverse solutions.

部署现实

当前可用的安装信号是:npm install adhd-agent。这只能作为起点,正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。

商业可用性

当前记录的许可证是 MIT。这是重要的商业使用信号,但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。

能力上限

Developers can build agents that generate a wide range of creative and non-obvious solutions for design decisions, fuzzy debugging, naming, API surface design, strategy, and any prompt requiring multiple approaches. Real-world use cases include generating diverse retry/timeout strategies, exploring alternative architectures, and surfacing novel ideas that a single-shot approach would miss. The ceiling is high for interdisciplinary and creative work where breadth and novelty are valued over quick, conventional answers.

来源与合规提示最近同步: Jul 31, 2026

Git-Stars 是独立产品,不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成,依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。

原始 GitHub 来源方法论编辑政策
编辑评估

UditAkhourii/adhd 被追踪为 TypeScript 项目,主要属于 AI Agent, LLM Tool, Developer Tool, UI Framework 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则,而不是复制项目文档。

增长检查:该仓库目前有 2.9k Star,今日 +0,本周 +791,本月 +0。这些窗口用于区分持续采用信号和短期曝光峰值。

维护检查:当前活跃度为 一般;最近一次推送距今 83 天,未关闭 Issue 为 14,约占总 Star 的 0.49%。这只是采用信号,不替代工程尽调。

采用检查:219 Fork 和 2.9k Watcher 反映项目被复用和关注的程度。许可证信号:MIT。商业或内部使用前请核验许可证兼容性。

适用判断:当你需要「AI 原型、LLM 工作流和 Agent 类应用」时,这个项目更值得评估;如果「需要法律审查、安全审计或生产 SLA 保证」,则需要谨慎。

来源检查:Git-Stars 当前为这份报告保留了 2 个明确来源引用,近期增长信号为 791。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。

证据清单

原创分析

充分

已经具备问题、能力和结论层面的原创判断。

来源

充分

已附带仓库元数据和 README/来源引用。

许可证

充分

已记录 MIT,可作为评估依据。

维护

充分

仓库元数据中可以看到近期活跃信号。

同类对比

充分

已有足够相近项目用于对比。

适合场景
  • AI 原型、LLM 工作流和 Agent 类应用
  • TypeScript 技术栈团队评估生态原生工具
谨慎使用场景
  • 需要法律审查、安全审计或生产 SLA 保证
采用信号

热度

2.9k 星标

复用

219 复刻

关注

2.9k 关注者

维护

moderate

许可证

MIT

未解决 Issue

14

项目概述

ADHD is an architectural fix for premature convergence in autoregressive reasoning, spawning isolated reasoning processes under deliberately distorted cognitive frames to generate diverse solutions for design decisions, debugging, and strategy tasks.

核心特性

- Spawns N isolated reasoning processes with zero shared context under distorted cognitive frames for divergent ideation - Runs a separate critic pass to score, cluster, prune traps, and deepen survivors - Generates 30+ ideas across clusters like economic-incentive, async-control-surface, and gamification, with non-obvious picks and trap detection

工具定位

AI Agent

Agent frameworks, autonomous workflows, and tool-use systems

LLM Tool

Libraries and tools for LLM apps, RAG, prompts, and evals

Developer Tool

Tools that improve coding, testing, build, and local workflow

UI Framework

Frontend frameworks, design systems, and interface libraries

快速开始
npm install adhd-agent
在 GitHub 上查看 项目主页
项目活跃度

63

健康评分

一般

提交活跃度

May 25, 2026

创建于

Jul 23, 2026

最近提交

来源轨迹

GitHub repository metadata

metadata

GitHub README

readme_summary

星标历史

每日同步积累数据后,Star 历史将在此显示。

社区健康度
219

复刻

14

未解决

2.9k

关注者

维护者
AD

UditAkhourii

GitHub 主页
主题与语言
TypeScriptadhdagentsaiai-agentsbrainstormchain-of-thoughtclaudeclaude-agent-sdkcreativitydivergent-thinkingideationinterdisciplinaryllmllm-toolsnodejsprompt-engineeringtree-of-thoughttypescript
生态与使用情况
GitHub 仓库 项目网站 Search on npm
同类对比

codecrafters-io/build-your-own-x

Master programming by recreating your favorite technologies from scratch.

540k

sindresorhus/awesome

😎 Awesome lists about all kinds of interesting topics

496k

freeCodeCamp/freeCodeCamp

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

454k

EbookFoundation/free-programming-books

:books: Freely available programming books

394k

nilbuild/developer-roadmap

Interactive roadmaps, guides and other educational content to help developers grow in their careers.

365k
许可证
MIT
创建于May 25, 2026
最近提交Jul 23, 2026
最近同步Jul 31, 2026
仓库规范

✓

许可证

✓

Fork 情况

~ 一般

维护情况

AI 深度分析由 Git-Stars 分析

解决的问题

ADHD solves the problem of premature convergence in linear Chain-of-Thought reasoning, where the model anchors on its first output. Unlike standard Tree-of-Thought, it spawns isolated reasoning processes with zero shared context during divergence, then uses a separate critic pass to score, cluster, prune traps, and deepen survivors, enabling more creative and diverse solutions.

能力范围

Developers can build agents that generate a wide range of creative and non-obvious solutions for design decisions, fuzzy debugging, naming, API surface design, strategy, and any prompt requiring multiple approaches. Real-world use cases include generating diverse retry/timeout strategies, exploring alternative architectures, and surfacing novel ideas that a single-shot approach would miss. The ceiling is high for interdisciplinary and creative work where breadth and novelty are valued over quick, conventional answers.

结论

ADHD is ideal for developers building coding agents that need creative, diverse, and non-obvious solutions, especially for open-ended problems. It should be avoided when speed and simplicity are paramount, as the parallel divergence adds overhead. The key trade-off is between breadth/novelty and efficiency/conventionality.

查看完整 AI 分析