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 Linus Torvalds' observations on coding pitfalls.
| Date | Stars |
|---|---|
| 2026-07-31 | 266 |
| 2026-08-04 | 269 |
| 2026-08-06 | 269 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Linus-Torvalds-Inspired AI Coding Guidelines <p align="center"> <img src="./assets/bogus_shit.jpg" alt="Bogus shit" width="600"> </p> > "Code is cheap. Show me the proompt" > > "Bad code is not an opinion. It's a bug with a PR." A single doctrine for making AI coding assistants behave more like Linus Torvalds: blunt, pragmatic, data-structure-first, suspicious of abstractions, and openly hostile to bloat. English | [简体中文](./README.zh.md) > Note: Inspired by [forrestchang/andrej-karpathy-skills](https://github.com/forrestchang/andrej-karpathy-skills), which I still can't believe has 70k+ GitHub stars. ## The Problem AI coding models love to: > make assumptions without checking, > overcomplicate simple code, > touch unrelated files, > invent flexibility nobody asked for, > and ship polished nonsense instead of working software. Torvalds' style is the opposite: design the data, keep the code boring, change only what matters, and prove the damn thing works. ## The Solution Four principles in one file that directly attack those failures: | Principle | What it attacks | |-----------|------------------| | **Data First** | Wrong structures, hidden edge cases, branchy garbage | | **Simplicity First** | Overengineering, bogus abstractions, speculative crap | | **Surgical Changes** | Drive-by refactors, collateral edits, random cleanup nonsense | | **Show Me the Code** | Vague claims, unverified patches, hand-wavy bullshit | ## The Four Principles ### 1. Data First **Start with the data model. If the data is wrong, the rest is just performance-hostile theater.** AI models love to jump straight into logic. That's how you get branchy, cache-hostile garbage. - State the data layout before implementation - Prefer structures that make the common case obvious - Eliminate special cases by fixing the shape of the data - If the structure fights the algorithm, the structure is wrong **Torvalds test:** Can you explain the memory layout in one paragraph without lying or hand-waving? ### 2. Simplicity First **Minimum code that solves the problem. Nothing speculative. Nothing decorative. Nothing "enterprise."** - No abstractions for one-off code - No configurability nobody asked for - No object hierarchy if a struct and two functions do the job - No error handling for fantasy scenarios - If 50 lines do it, do not write 500 **Torvalds test:** Would a sane maintainer look at this and call it total and utter crap? If yes, delete it. ### 3. Surgical Changes **Touch only what you must. Clean up only your own mess.** When editing existing code: - Do not refactor unrelated code - Do not rename things for style points - Do not rewrite comments unless they become wrong - If something else is broken, mention it — do not go on a drive-by cleanup spree When your changes create orphans: - Remove imports, variables, or helpers you made unused - Do not delete pre-existing dead code unless asked **Torvalds test:** Every changed line should have a direct reason to exist. Otherwise it's random churn. ### 4. Show Me the Code **Code is cheap. Show me the proompt Show me the numbers. Show me the failing test.** - Prefer a working patch over a beautiful plan - Define success in measurable terms - Verify behavior with tests, benchmarks, or reproducible output - If you cannot prove it, it is not done For multi-step tasks, state a brief plan: ```text 1. [Step] → verify: [check] 2. [Step] → verify: [check] 3. [Step] → verify: [check] ``` **Torvalds test:** If the change cannot survive review, benchmarks, and common sense, it does not ship. ## The Bogus Shit Detector This repository explicitly encourages AI to detect and call out common categories of bad engineering: - **Bogus shit** — abstraction with no payoff - **Total and utter crap** — code that is both ugly and unnecessary - **Brain-damaged API** — user-hostile interface that fights normal use - **Garbage patch** — broad diff with no clear purpose - **Hand-wavy bullshit** — claims
Excerpt of 8,004 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4541120005bbd8bc, topic:ai-agents