No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Astro-Han · Claude Skill · ★ 2.4k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is karpathy-llm-wiki safe to install? View the security audit →
Featured in: Obsidian for Claude Code & AI Agents
karpathy-llm-wiki One skill to build your own Karpathy-style LLM wiki. Install Works with Claude Code, Cursor, Codex, and other tools that support the Agent Skills standard. Quick Start 1. Ingest your first source Give the skill a URL, a file, or paste text directly: "Ingest this article: https://example.com/attention-is-all-you-need" The skill fetches the content into , then compiles it into a wiki article under . 2. Ask your wiki a question "What do I know about attention mechanisms?" The skill searches your wiki and answers with citations linking back to your articles. 3. Keep it healthy "Lint my wiki" The skill checks for broken links, missing index entries, stale cross-references, and reports potential issues. How It Works Inspired by Karpathy's LLM Wiki idea: "The LLM writes and maintains the wiki; the human reads and asks questions." The skill manages two directories in your project: your-project/ ├── raw/ ← Immutable source material (you or the LLM
| Stars | 2,404 |
| Forks | 286 |
| Language | Python |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 68.4658604342475/100 |
| Open Issues | 7 |
| Last Updated | 2026-07-23 |
| Created | 2026-04-05 |
| Platforms | claude-code, codex, python |
| Est. Tokens | ~14k |
These tools work well together with karpathy-llm-wiki for enhanced workflows:
Looking for a karpathy-llm-wiki alternative? If you're comparing karpathy-llm-wiki with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Bui
Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: htt
Claude Code plugin that generates individualized knowledge systems from conversation. You describe how you thi
Explore other popular claude skill tools:
karpathy-llm-wiki is Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.. It is categorized as a Claude Skill with 2.4k GitHub stars.
karpathy-llm-wiki is primarily written in Python. It covers topics such as agent-skill, claude-code, codex.
You can find installation instructions and usage details in the karpathy-llm-wiki GitHub repository at github.com/Astro-Han/karpathy-llm-wiki. The project has 2.4k stars and 286 forks, indicating an active community.
karpathy-llm-wiki is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to karpathy-llm-wiki on Agent Skills Hub include obsidian-wiki, swarmvault, compose-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: