karpathy repositories
Trending repositories tagged karpathy, ranked by trending score. Updated daily.
-
1
Dodaios/ste80-humanizer
STE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy shared.
GitHub · Python · 1,014 stars · 71 forks · +207 stars in 24 hours · Trending score 4.31
-
2
Ar9av/obsidian-wiki
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
GitHub · Python · 3,791 stars · 376 forks · +28 stars in 24 hours · Trending score 2.79
-
3
MehmetGoekce/llm-wiki
Build Karpathy's LLM Wiki with Claude Code. L1/L2 cache architecture. Logseq + Obsidian support.
GitHub · 170 stars · 30 forks · +23 stars in 24 hours · Trending score 2.36
-
4
Astro-Han/karpathy-llm-wiki
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
GitHub · Python · 2,778 stars · 318 forks · +6 stars in 24 hours · Trending score 1.74
-
5
atomicstrata/llm-wiki-compiler
The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
GitHub · TypeScript · 2,276 stars · 242 forks · +6 stars in 24 hours · Trending score 1.74
-
6
chizkidd/Karpathy-Neural-Networks-Zero-to-Hero
Detailed python notes & code for lectures and exercises of Andrej Karpathy's course "Neural Networks: Zero to Hero." The course is focused on building neural networks from scratch.
GitHub · Jupyter Notebook · 292 stars · 60 forks · 0 stars in 24 hours · Trending score 1.39
-
7
uditgoenka/autoresearch
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
GitHub · Shell · 6,850 stars · 492 forks · +4 stars in 24 hours · Trending score 1.31
-
8
GD4AI/obsidian-llm-wiki
Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
GitHub · TypeScript · 797 stars · 98 forks · 0 stars in 24 hours · Trending score 0.74
-
9
yologdev/yopedia
A wiki designed for both humans and agents to read and write.
GitHub · TypeScript · 76 stars · 16 forks · 0 stars in 24 hours · Trending score 0.24
-
10
ddsyasas/llm-wiki
Open source local-first knowledge base maintained by an LLM agent. Implements Andrej Karpathy's LLM Wiki pattern.
GitHub · TypeScript · 73 stars · 20 forks · 0 stars in 24 hours · Trending score 0.14
-
11
lucasastorian/llmwiki
Open Source Implementation of Karpathy's LLM Wiki. Upload documents, connect your Claude account via MCP, and have it write your wiki !
GitHub · Python · 1,766 stars · 247 forks · 0 stars in 24 hours · Trending score 0.03
-
12
zosmaai/pi-llm-wiki
Self-maintaining, Obsidian-compatible knowledge base for pi — turn raw sources into an interlinked wiki that compounds. Native Open Knowledge Format (OKF) v0.2.
GitHub · TypeScript · 617 stars · 50 forks · 0 stars in 24 hours · Trending score 0.00
-
13
2233admin/obsidian-llm-wiki
Your markdown vault, compiled into a 6-persona MCP team for Claude Code, Codex, OpenCode, and Gemini CLI. Headless-first. Cites, doesn't guess.
GitHub · TypeScript · 38 stars · 13 forks · 0 stars in 24 hours · Trending score 0.00
-
14
CodeDeficient/KarpeSlop
A linter for the mistakes AI coding tools leave in TypeScript and JavaScript: imports that don’t exist, missing packages, placeholder code, swallowed errors and unsafe casts.
GitHub · TypeScript · 39 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
15
ddenzu/karpathy-llm-wiki-second-brain
Obsidian + Claude Code template: Karpathy's LLM Wiki as a 4-axis second brain
GitHub · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
16
tundergod/tundergod-loop
Run a Karpathy-style planner/generator/evaluator agent loop in your repo: a manager negotiates a testable contract, then drives a resumable background runner.
GitHub · Python · 5 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
17
Lucas-Grilli/Context_OS
The local system that remembers your projects, maintains itself, and is ready in 5 minutes. But, most of all, a Second Brain that doesn't become a Second Job.
GitHub · 9 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
18
ChangWenC/understanding-ladder
Karpathy's understanding ladder as agent skills: auto-pick text, diagram, interactive HTML, or video storyboard for any explanation. Nothing cut. English + 中文.
GitHub · 121 stars · 4 forks · 0 stars in 24 hours · Trending score 0.00
-
19
FutureAtoms/karpathy-ladder
Unofficial Claude Code skill after Andrej Karpathy's post: explain anything as ASD-STE100 prose, a diagram, an engineering-drawing spec sheet or a narrated 3Blue1Brown-style video.
GitHub · Python · 9 stars · 2 forks · 0 stars in 24 hours · Trending score 0.00
-
20
JAICHANGPARK/ASD-STE100
ASD-STE100 (Simplified Technical English, Issue 9) for Claude Code: /asd mod with an STE pane, agent skill, and linter. Inspired by Karpathy's "80% ASD-STE100" tip.
GitHub · JavaScript · 22 stars · 3 forks · 0 stars in 24 hours · Trending score 0.00
-
21
openapi/gknowledge
🐧 A native GNOME knowledge workstation that turns documents into evolving AI-assisted knowledge bases.
GitHub · Python · 23 stars · 5 forks · 0 stars in 24 hours · Trending score 0.00
-
22
zhurudong/andrej-karpathy-llm-wiki
A minimal CLAUDE.md template that turns any LLM CLI into a personal knowledge base. Drop in one file, start ingesting articles. Karpathy's LLM Wiki pattern.
GitHub · Shell · 32 stars · 7 forks · 0 stars in 24 hours · Trending score 0.00
-
23
milanm/AutoGrad-Engine
A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies
GitHub · C# · 402 stars · 48 forks · 0 stars in 24 hours · Trending score 0.00
-
24
helloianneo/obsidian-ai-second-brain
Obsidian + Claude AI 个人知识库完整搭建指南 | 基于 Karpathy LLM Wiki 方法论 | 4 阶段 12 步 | 不用写代码
GitHub · 300 stars · 29 forks · 0 stars in 24 hours · Trending score 0.00