Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
-
Updated
Apr 6, 2026 - Shell
#
karpathy
Here are 120 public repositories matching this topic...
A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.
awesome-list autonomous-agents ai-agents karpathy ai-research scientific-discovery ai-tools llm-agents agentic-systems research-agents claude-code self-improving-systems karpathy-inspired autoresearch experiment-loops
-
Updated
Apr 4, 2026
The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.
markdown cli compiler wiki knowledge-base obsidian karpathy knowledge-compilation llm context-engineering
-
Updated
Apr 8, 2026 - TypeScript
A complete GPT language model (training and inference) in ~600 lines of pure C#, zero dependencies
machine-learning ai deep-learning csharp neural-network dotnet autograd transformer gpt language-model backpropagation karpathy
-
Updated
Feb 14, 2026 - C#
Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.
markdown productivity cursor knowledge-base personal-knowledge-base knowledge-management codex karpathy llm claude-code rag-alternative agent-skill llm-wiki
-
Updated
Apr 13, 2026
Inspired by Karpathy's LLM Wiki. Local-first RAG knowledge base compiler with MCP server (Claude Code, Codex, OpenCode, OpenClaw). Turn raw research into a persistent markdown wiki, knowledge graph, and hybrid search that compound over time.
wiki mcp opencode embeddings knowledge-graph obsidian pkm codex ai-agents karpathy rag local-first llm mcp-server claude-code claude-skills codex-skills opencode-skills openclaw llm-wiki
-
Updated
Apr 12, 2026 - TypeScript
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.
python nlp deep-learning neural-network tokenizer jupyter-notebook pytorch transformer educational gpt lecture language-model pytorch-tutorial karpathy andrej neural-networks-from-scratch pytorch-implementation micrograd zero-to-hero nn-zero-to-hero
-
Updated
Feb 28, 2026 - Jupyter Notebook
GPT in a QR Code ; The actual most atomic way to train and inference a GPT in pure, dependency-free JS/Python.
javascript python machine-learning ai artificial-intelligence minification gpt karpathy microgpt decompressionstream picogpt
-
Updated
Feb 17, 2026 - HTML
Karpathy’s LLM Wiki, 100% local with Ollama. Drop Markdown notes → AI extracts concepts → your Obsidian wiki auto-links and grows. Zero cloud. Zero sharing. Your notes stay yours.
knowledge-base obsidian pkm markdown-wiki karpathy second-brain personal-knowledge-management local-llm llm-tools ollama llm-pipeline obsidian-wiki obsidian-llm rag-alternative rag-local git-based-wiki self-hosted-wiki local-first-ai llm-knowledge-base llm-wiki
-
Updated
Apr 12, 2026 - Python
LLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.
python markdown cli open-source ai wiki mcp static-site developer-tools cursor knowledge-base obsidian copilot karpathy session-history llm gemini-cli claude-code codex-cli llm-wiki
-
Updated
Apr 9, 2026 - Python
Memoriki - LLM Wiki + MemPalace. Personal knowledge base with real memory.
mcp knowledge-base obsidian personal-wiki karpathy second-brain llm claude-code rag-alternative mempalace
-
Updated
Apr 14, 2026
The Karpathy treatment for OpenClaw - stripped to ε. 515 lines of Python, 6 files, one dependency.
python ai minimal telegram-bot personal-assistant educational ai-agents karpathy ai-assistant llm react-agent tool-calling karpathy-inspired openclaw
-
Updated
Mar 26, 2026 - Python
Build Karpathy's LLM Wiki with Claude Code. L1/L2 cache architecture. Logseq + Obsidian support.
-
Updated
Apr 10, 2026 - Shell
Train Llama 3 models from scratch. Any scale, any personality. By Arianna Method.
training go golang machine-learning ai deep-learning transformers pytorch transformer llama from-scratch personality karpathy llm llamacpp gguf llama3 nanochat nanollama
-
Updated
Mar 30, 2026 - Python
Train your own ChatGPT on Apple Silicon — MLX port of nanochat
training macos machine-learning deep-learning transformer gpt language-model mlx karpathy sft apple-silicon llm chatgpt nanochat
-
Updated
Apr 11, 2026 - Python
A git template for building your own LLM-powered personal wiki. Training period, metadata standard, lint system included. Clone and go.
-
Updated
Apr 13, 2026 - Python
The Self-Growing Karpathy LLM Wiki — grown by an AI agent yoyo from Karpathy's founding prompt
-
Updated
Apr 14, 2026 - TypeScript
⚡ The AI Slop Index linter inspired by @karpathy. Detects hallucinated imports, any-type abuse, vibe coding, and soul-less patterns in TypeScript/JavaScript/React. Fast (~4s), educational, CI-ready. npx karpeslop@latest
javascript typescript linting linter static-analysis developer-tools code-review code-quality copilot karpathy ai-tools ai-generated-code ai-detection
-
Updated
Apr 4, 2026 - TypeScript
Autonomous goal-directed iteration for Gemini CLI. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
-
Updated
Mar 27, 2026 - JavaScript
Improve this page
Add a description, image, and links to the karpathy topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the karpathy topic, visit your repo's landing page and select "manage topics."