Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats

Bifrost
Bifrost
ClawBench
ClawBench
Busbar
Busbar

UditAkhourii/adhd

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.

#AI skills
Visit GitHub
TypeScript
4.5k
332
2 contributors
MIT License
website
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

ClawBench

a benchmark for personal agents

Busbar

Control what AI can do before it acts

Momentum

How fast UditAkhourii/adhd is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Aug 24 – Oct 23, 2026

Stars +543 in 61 days

02040
35

Forks +53 in 61 days

0246
5

Merged PRs 2 in 61 days

01
1

Trendshift Trendingwhere the repository ranked each day it made the top 25

Not in the Trendshift top 25 in this period

Aug 24Sep 1Sep 9Sep 17Sep 25Oct 3Oct 11Oct 19
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRs
Mon, Aug 24, 2026+11+00
Tue, Aug 25, 2026+17+10
Wed, Aug 26, 2026+13+00
Thu, Aug 27, 2026+15+20
Fri, Aug 28, 2026+12+10
Sat, Aug 29, 2026+13+10
Sun, Aug 30, 2026+9+00
Mon, Aug 31, 2026+5+10
Tue, Sep 1, 2026+13+00
Wed, Sep 2, 2026+17+10
Thu, Sep 3, 2026+4+20
Fri, Sep 4, 2026+9+00
Sat, Sep 5, 2026+7+20
Sun, Sep 6, 2026+10+00
Mon, Sep 7, 2026+9+00
Tue, Sep 8, 2026+22+00
Wed, Sep 9, 2026+24+50
Thu, Sep 10, 2026+9+00
Fri, Sep 11, 2026+16+30
Sat, Sep 12, 2026+9+00
Sun, Sep 13, 2026+6+00
Mon, Sep 14, 2026+6+20
Tue, Sep 15, 2026+12+10
Wed, Sep 16, 2026+7+00
Thu, Sep 17, 2026+35+01
Fri, Sep 18, 2026+15+20
Sat, Sep 19, 2026+3+10
Sun, Sep 20, 2026+12+00
Mon, Sep 21, 2026+4+00
Tue, Sep 22, 2026+9+10
Wed, Sep 23, 2026+7+10
Thu, Sep 24, 2026+7+00
Fri, Sep 25, 2026+8+00
Sat, Sep 26, 2026+3+10
Sun, Sep 27, 2026+4+00
Mon, Sep 28, 2026+7+00
Tue, Sep 29, 2026+7+00
Wed, Sep 30, 2026+5+00
Thu, Oct 1, 2026+13+30
Fri, Oct 2, 2026+12+00
Sat, Oct 3, 2026+4+00
Sun, Oct 4, 2026+4+00
Mon, Oct 5, 2026+1+01
Tue, Oct 6, 2026+7+10
Wed, Oct 7, 2026+8+20
Thu, Oct 8, 2026+8+00
Fri, Oct 9, 2026+5+10
Sat, Oct 10, 2026+4+00
Sun, Oct 11, 2026+7+20
Mon, Oct 12, 2026+11+10
Tue, Oct 13, 2026+10+00
Wed, Oct 14, 2026+11+20
Thu, Oct 15, 2026+2+00
Fri, Oct 16, 2026+4+30
Sat, Oct 17, 2026+1+20
Sun, Oct 18, 2026+5+30
Mon, Oct 19, 2026+10+30
Tue, Oct 20, 2026+4+10
Wed, Oct 21, 2026+0+10
Thu, Oct 22, 2026+7+00
Fri, Oct 23, 2026+4+00
Total+543+532
  • 1#1 on the list
  • 7Rank that day
  • Not trending
  • Mentions and achievements

    Where people are talking about UditAkhourii/adhd, and every badge it has earned
    1. Oct 141 post
      • 😖 AI 写代码越写越跑偏?ADHD 给编程 agent 装了「专注」:思路树加剪枝,在几个方向里挑最靠谱的,偏了就砍。

        Read full on X, posted by @laogeai

        @laogeai · x.com

    2. 1 month earlier
    3. Sep 61 post
      • Tree-of-thought still walks one shared context, so whatever the model says first anchors every branch. A newer coding-agent skill fixes that by giving each branch zero shared context instead, then…

        Read full on X, posted by @0xJ4yD3v

        @0xJ4yD3v · x.com

    4. 1 month earlier
    5. Aug 31 post
      • Someone just ran Kimi k3 with 2.78 trillion parameter on a single CPU in 8.24 GB of RAM. 100% Opensource.

        Read full on X, posted by @Saboo_Shubham_

        @Saboo_Shubham_ · x.com

    6. 14 days earlier
    7. Jul 202 posts3 posts
      • Someone just gave Claude Code ADHD... and the results are surprisingly good. Instead of locking onto the first idea, this open-source skill makes AI agents explore multiple independent reasoning…

        Read full on X, posted by @DivyanshT91162

        @DivyanshT91162 · x.com

      • SOMEONE LITERALLY OPEN-SOURCED AN ADHD AGENT SKILL FOR CLAUDE CODE .. and it completely rewires how agents handle fuzzy debugging, naming, and API design. The problem with standard autoregressive…

        Read full on X, posted by @DataChaz

        @DataChaz · x.com

      • Someone just created an ADHD agent skill for Claude Code. 100% Opensource.

        Read full on X, posted by @Saboo_Shubham_

        @Saboo_Shubham_ · x.com

    8. 1 month earlier
    9. Jun 111 post
      • • Spawns N parallel isolated agent calls with zero shared context during divergence • Separate critic pass scores, clusters, prunes traps, and deepens survivors • One-command install auto-detects…

        Read full on X, posted by @the_osps

        @the_osps · x.com

    10. Jun 71 post
      • - UditAkhourii/adhd ( (★62) — ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude Agent SDK. Fans out parallel divergent thoughts under different cognitive…

        Read full on X, posted by @finguru1980

        @finguru1980 · x.com

    11. 9 days earlier
    12. May 292 posts
      • ADHD for coding agents - undocks LLM reasoning from its first guess. - Fans out N isolated threads under distorted cognitive frames - Zero shared context during divergence - Critic pass scores,…

        Read full on X, posted by @deucesync

        @deucesync · x.com

      • UditAkhourii 开源 adhd 「让 AI Agent 学会发散思维」 上线 4 天 493+ stars。把 Tree-of-Thought 做成 Claude Agent SDK 的 skill,并行多路思维分支 + 自动打分剪枝,只留最优解。 Agent 终于会 brainstorming 了。 #AI #Agent #Claude #开源

        Read full on X, posted by @486vs101

        @486vs101 · x.com

    You might also like

    Repositories close to UditAkhourii/adhd
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

    Enterprise AI Gateway Built For Scale: Route, Govern, and Secure All Your AI Traffic

    Busbar

    Control what AI can do before it acts

    ClawBench

    a benchmark for personal agents

    danium/lateral-thinking

    Lateral thinking skills for AI agents - 8 techniques + a router. de Bono for your coding agent.

    32525

    K-Dense-AI/mimeographs

    Python

    Ready-to-use agent skills that clone the thinking of founders, philosophers, and scientists into your agent. Generated with K-Dense-AI/mimeo.

    13120

    SnakeO/claude-co-commands

    Shell

    Co-* planning, validation, and brainstorming commands for Claude Code via Codex MCP

    14810

    agentara/skills

    HTML

    Original and practical skills for AI builders.

    61547

    Azzedde/brainstormers

    TypeScript

    This repository hosts a suite of specialized agents designed to power your brainstorming sessions. Each agent brings a unique perspective and tailored approach to generate creative, targeted solutions for diverse challenges. Choose the right agent for your specific brainstorming needs and unlock innovative ideas with precision.

    64173

    vtemian/octto

    TypeScript

    Interactive brainstorming UI for OpenCode agents - multi-question forms, decisions, and real-time feedback

    52531

    skymanbp/cc-tree

    Python

    Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adversarial critique, and design-space exploration. 12 framings × hard-ban-on-incomplete-leaves × stable convergence.

    94

    CL-ML/open-collider

    Python

    A semantic collision engine for non-trivial LLM idea generation. Operationalizes Koestler's bisociation theory (1964): injects structurally distant knowledge domains into the prompt, forces collisions, surfaces non-trivial ideas. Empirical validation in CL-ML/open-collider-research.

    34436

    xixu-me/prompt-library

    Python

    Comprehensive collection of professional AI prompts across various categories

    14420