Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
| Date | Stars |
|---|---|
| 2026-07-31 | 94653 |
| 2026-08-08 | 96794 |
| 2026-08-17 | 98543 |
| 2026-08-18 | 98866 |
| 2026-08-19 | 99137 |
| 2026-08-20 | 99364 |
| 2026-08-21 | 99916 |
| 2026-08-22 | 100243 |
| 2026-08-23 | 100419 |
| 2026-08-24 | 100617 |
| 2026-08-25 | 100806 |
| 2026-08-26 | 101069 |
| 2026-08-27 | 101318 |
| 2026-08-28 | 101543 |
| 2026-08-29 | 101699 |
| 2026-08-30 | 101804 |
| 2026-08-31 | 101971 |
| 2026-09-01 | 102161 |
| 2026-09-02 | 102376 |
| 2026-09-03 | 102885 |
| 2026-09-04 | 103360 |
| 2026-09-05 | 103731 |
| 2026-09-06 | 103863 |
| 2026-09-07 | 104042 |
| 2026-09-08 | 104256 |
| 2026-09-09 | 104459 |
| 2026-09-10 | 104653 |
| 2026-09-11 | 104849 |
| 2026-09-12 | 105153 |
| 2026-09-13 | 105295 |
| 2026-09-14 | 105488 |
| 2026-09-15 | 105687 |
| 2026-09-16 | 105892 |
| 2026-09-17 | 106204 |
| 2026-09-18 | 106467 |
| 2026-09-19 | 106684 |
| 2026-09-20 | 106886 |
| 2026-09-21 | 107088 |
| 2026-09-22 | 107281 |
| 2026-09-23 | 107475 |
| 2026-09-24 | 107644 |
| 2026-09-25 | 107791 |
| 2026-09-26 | 107898 |
| 2026-09-27 | 108005 |
| 2026-09-28 | 108140 |
| 2026-09-29 | 108290 |
| 2026-09-30 | 108504 |
| 2026-10-01 | 108657 |
| 2026-10-02 | 108853 |
| 2026-10-03 | 109308 |
| 2026-10-04 | 109716 |
| 2026-10-05 | 109909 |
| 2026-10-06 | 110101 |
| 2026-10-07 | 110330 |
| 2026-10-08 | 110504 |
| 2026-10-09 | 110682 |
| 2026-10-10 | 110858 |
| 2026-10-11 | 110980 |
| 2026-10-12 | 111153 |
| 2026-10-13 | 111352 |
| 2026-10-14 | 111669 |
| 2026-10-15 | 112083 |
| 2026-10-16 | 112965 |
| 2026-10-17 | 113158 |
| 2026-10-18 | 113373 |
| 2026-10-19 | 113578 |
| 2026-10-20 | 113770 |
| 2026-10-21 | 113997 |
| 2026-10-22 | 114275 |
| 2026-10-23 | 114528 |
| 2026-10-24 | 114728 |
| 2026-10-25 | 114919 |
| 2026-10-26 | 115168 |
| 2026-10-27 | 115425 |
| 2026-10-28 | 115668 |
| 2026-10-29 | 115937 |
| 2026-10-30 | 116226 |
| 2026-10-31 | 116434 |
| 2026-11-01 | 116606 |
| 2026-11-02 | 116838 |
| 2026-11-03 | 117079 |
| 2026-11-04 | 117379 |
Today
+300 stars today
This week
+1.7k stars this week
This month
+7.5k stars this month
Momentum
3276.0
growth rate 1.48%/day
<div align="center"> <img src="docs/assets/caveman-logo-banner.png" alt="Caveman" width="720"> # why many token when few do trick **Caveman make your AI agent say less and read less. Code stay exact. Brain still big.** <a href="https://github.com/JuliusBrussee/caveman/stargazers"><img src="https://img.shields.io/github/stars/JuliusBrussee/caveman?style=flat-square&color=F0A63C&label=stars" alt="GitHub stars"></a> <a href="https://www.npmjs.com/package/@caveman-ai/cli"><img src="https://img.shields.io/npm/dm/@caveman-ai/cli?style=flat-square&color=F0A63C&label=cli%20downloads" alt="npm downloads"></a> <a href="./INSTALL.md"><img src="https://img.shields.io/badge/works_with-30%2B_agents-orange?style=flat-square" alt="30+ agents"></a> <a href="#license"><img src="https://img.shields.io/badge/license-Apache--2.0-green?style=flat-square" alt="License"></a> <table> <tr> <td align="center" width="25%"><h3>33.2% fewer</h3>input tokens, whole sessions<br><sub><a href="#read-less-332-fewer-input-tokens">54 Claude Code runs</a>, 18 of 18 answers right</sub></td> <td align="center" width="25%"><h3>54% cheaper</h3>with Auto, same score<br><sub><a href="#auto-54-cheaper-same-score">85 coding tasks</a> vs Opus 5.5 at xhigh, interim</sub></td> <td align="center" width="25%"><h3>397 → 76</h3>tokens for one test run<br><sub><a href="#blocks-code-mode-script-written-once">Blocks</a> vs <code>| tail -20</code></sub></td> <td align="center" width="25%"><h3>1.4 to 2.4× cheaper</h3>with caveman-style output<br><sub><a href="https://arxiv.org/abs/2606.24083">Adobe Research</a>, eight models</sub></td> </tr> </table> Cited by **[Adobe Research](https://arxiv.org/abs/2606.24083)** · A/B tested by **[JetBrains](https://blog.jetbrains.com/ai/2026/07/speak-to-ai-agents-like-cavemen-tosave-tokens/)** · Remade for Elasticsearch on **[Elasticsearch Labs](https://www.elastic.co/search-labs/blog/elastic-caveman-ai-token-reduction)**<br> **#1** on [Hacker News](https://news.ycombinator.com/item?id=47647455) · **#1** on GitHub Trending · *"No way this actually works."* [ThePrimeagen](https://www.youtube.com/watch?v=L29q2LRiMRc) **[Install](#install) · [Six rocks](#six-rocks-one-install) · [Proof](#proof) · [Say less](#say-less-the-caveman-voice) · [Read less](#read-less-332-fewer-input-tokens) · [Auto](#auto-54-cheaper-same-score) · [Blocks](#blocks-code-mode-script-written-once) · [Commands](#commands) · [Caveman Cloud](#caveman-cloud)** </div> --- <table> <tr> <th width="50%">Normal agent · 63 tokens</th> <th width="50%"><img src="docs/assets/dancing-rock.svg" width="18" height="18" alt=""> Caveman agent · 20 tokens</th> </tr> <tr> <td valign="top"> > The reason your React component is re-rendering is likely because you're creating a new object reference on each render cycle. When you pass an inline object as a prop, React's shallow comparison sees it as a different object every time, which triggers a re-render. I'd recommend using useMemo to memoize the object. </td> <td valign="top"> > New object ref each render, so React re-renders. Wrap the prop in `useMemo`. </td> </tr> </table> **Same fix. 63 token become 20. Brain still big.** Pick your club: | Skill | Same answer | Tokens | |---|---|---:| | `/caveman` | New object ref each render, so React re-renders. Wrap the prop in `useMemo`. | 20 | | `/ultracave` | Inline object prop, new ref, re-render. `useMemo`. | 14 | | `/megacave` | 新參照致重繪。`useMemo`。 | **13** | <sub>Token counts: tiktoken o200k.</sub> ## Install ```bash npx @caveman-ai/cli@latest ``` One command. Mac, Linux, Windows. Caveman find your agents and your logins, show what it change. Press Enter. Done. Needs Node.js 22.13+. After that, plain `claude` stays caveman'd. So do Codex, Gemini CLI, OpenCode, and [30+ more](./INSTALL.md). It runs on your machine, with your keys and your Claude Pro/Max login. One rock. That it. <sub>Had caveman before 4.0? Say <code>@latest</code>, or the old copy on your machine wins. Already set up?
Excerpt of 22,520 characters
Read on GitHub
Julius Brussee · Netherlands
172
Seba Breguel · Vambe AI · Chile
9
9
Amir Fathi · FastInfer Inc. · Canada
8
vraj patel
5
Matthias Humt · @DLR-RM · Germany
4
3
Leo · Beijing Jiaotong University
3
Arek Gladki · Poland
3
2
Ben Younes · Freelance · France
2
.jcrakcrn · JCCIDC · United States
2
David · Yoco / @Dyner-AI · South Africa
2
2
Fezan Muhammad Ali · Pakistan
1
Dmitrii Malakhov · Independent AI Engineer · Serbia
1
Dennis Neufeld · @innogames · Germany
1
Matt Van Horn
1
Vagesh
1
Shayne Sweeney · OpenAI · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4791aced6643283e, topic:llm
matched fp:4791aced6643283e, topic:prompt-engineering