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.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
| Date | Stars |
|---|---|
| 2026-08-01 | 197934 |
| 2026-08-06 | 200055 |
| 2026-08-14 | 202174 |
| 2026-08-18 | 203517 |
| 2026-08-19 | 203801 |
| 2026-08-20 | 204180 |
| 2026-08-21 | 204726 |
| 2026-08-22 | 205026 |
| 2026-08-23 | 205578 |
| 2026-08-24 | 206128 |
| 2026-08-25 | 206917 |
| 2026-08-26 | 207509 |
| 2026-08-27 | 207899 |
| 2026-08-28 | 208289 |
| 2026-08-29 | 208530 |
| 2026-08-30 | 208791 |
| 2026-08-31 | 209029 |
| 2026-09-01 | 209264 |
| 2026-09-02 | 209536 |
| 2026-09-03 | 209806 |
| 2026-09-04 | 210051 |
| 2026-09-05 | 210269 |
| 2026-09-06 | 210520 |
| 2026-09-07 | 210785 |
| 2026-09-08 | 211087 |
| 2026-09-09 | 211769 |
| 2026-09-10 | 212012 |
| 2026-09-11 | 212232 |
| 2026-09-12 | 212508 |
| 2026-09-13 | 212696 |
| 2026-09-14 | 212892 |
| 2026-09-15 | 213112 |
| 2026-09-16 | 213323 |
| 2026-09-17 | 213532 |
| 2026-09-18 | 213864 |
| 2026-09-19 | 214067 |
| 2026-09-20 | 214257 |
| 2026-09-21 | 214445 |
| 2026-09-22 | 214593 |
| 2026-09-23 | 214739 |
| 2026-09-24 | 214933 |
| 2026-09-25 | 215073 |
| 2026-09-26 | 215258 |
| 2026-09-27 | 215458 |
| 2026-09-28 | 215636 |
| 2026-09-29 | 215801 |
| 2026-09-30 | 215989 |
| 2026-10-01 | 216114 |
| 2026-10-02 | 216497 |
| 2026-10-03 | 216655 |
| 2026-10-04 | 216787 |
| 2026-10-05 | 216962 |
| 2026-10-06 | 217178 |
| 2026-10-07 | 217366 |
| 2026-10-08 | 217540 |
| 2026-10-09 | 217622 |
| 2026-10-10 | 217867 |
| 2026-10-11 | 218660 |
| 2026-10-12 | 219097 |
| 2026-10-13 | 219379 |
| 2026-10-14 | 219648 |
| 2026-10-15 | 219960 |
| 2026-10-16 | 220233 |
| 2026-10-17 | 220482 |
| 2026-10-18 | 220825 |
| 2026-10-19 | 221097 |
| 2026-10-20 | 221375 |
| 2026-10-21 | 221700 |
| 2026-10-22 | 222228 |
| 2026-10-23 | 222737 |
| 2026-10-24 | 223139 |
| 2026-10-25 | 223540 |
| 2026-10-26 | 224145 |
| 2026-10-27 | 225178 |
| 2026-10-28 | 225749 |
| 2026-10-29 | 226207 |
| 2026-10-30 | 226645 |
| 2026-10-31 | 227174 |
| 2026-11-01 | 227738 |
| 2026-11-02 | 228293 |
| 2026-11-03 | 228829 |
| 2026-11-04 | 229301 |
Today
+472 stars today
This week
+3.6k stars this week
This month
+12k stars this month
Momentum
5320.0
growth rate 1.57%/day
# Karpathy-Inspired Claude Code Guidelines
> Check out my new project [Multica](https://github.com/multica-ai/multica) — an open-source platform for running and managing coding agents with reusable skills.
>
> Follow me on X: [https://x.com/jiayuan_jy](https://x.com/jiayuan_jy)
A single `CLAUDE.md` file to improve Claude Code behavior, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.
English | [简体中文](./README.zh.md)
## The Problems
From Andrej's post:
> "The models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should."
> "They really like to overcomplicate code and APIs, bloat abstractions, don't clean up dead code... implement a bloated construction over 1000 lines when 100 would do."
> "They still sometimes change/remove comments and code they don't sufficiently understand as side effects, even if orthogonal to the task."
## The Solution
Four principles in one file that directly address these issues:
| Principle | Addresses |
|-----------|-----------|
| **Think Before Coding** | Wrong assumptions, hidden confusion, missing tradeoffs |
| **Simplicity First** | Overcomplication, bloated abstractions |
| **Surgical Changes** | Orthogonal edits, touching code you shouldn't |
| **Goal-Driven Execution** | Leverage through tests-first, verifiable success criteria |
## The Four Principles in Detail
### 1. Think Before Coding
**Don't assume. Don't hide confusion. Surface tradeoffs.**
LLMs often pick an interpretation silently and run with it. This principle forces explicit reasoning:
- **State assumptions explicitly** — If uncertain, ask rather than guess
- **Present multiple interpretations** — Don't pick silently when ambiguity exists
- **Push back when warranted** — If a simpler approach exists, say so
- **Stop when confused** — Name what's unclear and ask for clarification
### 2. Simplicity First
**Minimum code that solves the problem. Nothing speculative.**
Combat the tendency toward overengineering:
- No features beyond what was asked
- No abstractions for single-use code
- No "flexibility" or "configurability" that wasn't requested
- No error handling for impossible scenarios
- If 200 lines could be 50, rewrite it
**The test:** Would a senior engineer say this is overcomplicated? If yes, simplify.
### 3. Surgical Changes
**Touch only what you must. Clean up only your own mess.**
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting
- Don't refactor things that aren't broken
- Match existing style, even if you'd do it differently
- If you notice unrelated dead code, mention it — don't delete it
When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused
- Don't remove pre-existing dead code unless asked
**The test:** Every changed line should trace directly to the user's request.
### 4. Goal-Driven Execution
**Define success criteria. Loop until verified.**
Transform imperative tasks into verifiable goals:
| Instead of... | Transform to... |
|--------------|-----------------|
| "Add validation" | "Write tests for invalid inputs, then make them pass" |
| "Fix the bug" | "Write a test that reproduces it, then make it pass" |
| "Refactor X" | "Ensure tests pass before and after" |
For multi-step tasks, state a brief plan:
```
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
```
Strong success criteria let the LLM loop independently. Weak criteria ("make it work") require constant clarification.
## Install
**Option A: Claude Code Plugin (recommended)**
From within Claude Code, first add the marketplace:
```
/plugin marketplace add forrestchang/andrej-karpathy-skills
```
Then install the plugin:
```
/plugin install andrej-karpathy-skills@Excerpt of 6,162 characters
Read on GitHub
Jiayuan Zhang · @multica-ai
17
Shehab Tarek · Egypt
5
2
1
1
josepha_mayo
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ebb954b8e5df119e, llm:Description: 'A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.'