karpathy-llm-wiki
A reusable skill for building Karpathy-style LLM wikis with Claude Code, Cursor, Codex, and other Agent Skills tools.
    
<p align="center"> <img src="assets/karpathy-tweet.png" alt="Karpathy's tweet about LLM Wiki" width="560"> </p>
karpathy-llm-wiki packages Karpathy's LLM Wiki idea into one installable Agent Skills skill. Your coding agent ingests sources into raw/, compiles durable knowledge pages into wiki/, answers questions with citations, and lints the wiki for consistency.
What Is an LLM Wiki?
An LLM wiki is a knowledge system where the LLM maintains structured wiki pages instead of re-searching raw documents on every question. New sources are compiled into durable markdown pages, cross-references are updated over time, and answers cite the wiki pages that already contain the synthesized knowledge.
This skill gives you three operations:
| Operation | What it does | Output | |-----------|--------------|--------| | Ingest | Collects a source into raw/, triages it, then creates or updates wiki articles — or just logs it when nothing is new | New or updated wiki pages | | Query | Searches the wiki and answers with citations | Grounded answers linking to markdown pages | | Lint | Checks index integrity, links, and wiki health | Auto-fixes plus reported issues |
See SKILL.md for the full skill specification.
LLM Wiki vs RAG
| Approach | Knowledge lives in | When synthesis happens | Good for | |----------|--------------------|------------------------|----------| | RAG | Raw chunks and embeddings | At query time | Broad retrieval across large corpora | | LLM Wiki | Curated markdown pages | During ingest and maintenance | Compounding knowledge, summaries, and durable cross-links |
This skill is optimized for the wiki model: knowledge that improves over time instead of re-deriving relationships on every query.
Usage Stats
Based on a production knowledge base maintained daily since April 2026:
- 94 wiki articles across 13 topic directories
- 99 source materials ingested
- 87 operation log entries in the last 7 days
See examples/ for sample wiki pages, source files, and operation logs.
Install
npx add-skill Astro-Han/karpathy-llm-wikiWorks with any tool that supports the Agent Skills standard.
Quick Start
1. Ingest your first source
Give the skill a URL, a file, or pasted text:
> "Ingest this article: https://example.com/attention-is-all-you-need"
The skill stores the source in raw/, then compiles or updates the right knowledge pages in wiki/.
2. Ask your wiki a question
> "What do I know about attention mechanisms?"
The skill searches the wiki and answers with citations linking back to your markdown pages.
3. Keep the wiki healthy
> "Lint my wiki"
Checks for broken links, missing index entries, stale cross-references, and related issues.
How the Workflow Works
The core idea from Karpathy: the LLM maintains the wiki while the human focuses on choosing sources and asking good questions.
your-project/
├── raw/ ← Immutable source material
│ └── topic/
│ └── 2026-04-03-source-article.md
├── wiki/ ← Compiled knowledge pages maintained by the LLM
│ ├── topic/
│ │ └── concept-name.md
│ ├── index.md ← Global table of contents
│ └── log.md ← Append-only operation logEach new source can update multiple pages, strengthen cross-references, and record contradictions. That is what makes the wiki compound over time.
Tool Compatibility
This skill follows the agentskills.io open standard:
| Tool | Install method | |------|----------------| | Claude Code | npx add-skill Astro-Han/karpathy-llm-wiki | | Cursor | npx add-skill Astro-Han/karpathy-llm-wiki | | Codex CLI | Copy to .agents/skills/karpathy-llm-wiki/ | | OpenCode | npx add-skill Astro-Han/karpathy-llm-wiki | | Other tools | Copy SKILL.md, references/, and scripts/ into the tool's skill directory |
FAQ
What is the difference between an LLM wiki and a personal wiki?
An LLM wiki is maintained by the model. It updates summaries, cross-links, index entries, and contradictions as new material arrives. A normal personal wiki depends on manual editing.
What sources can I ingest?
Web pages, papers, blog posts, PDFs, markdown files, text files, and pasted text. The skill converts everything into markdown under raw/ and compiles it into wiki/.
Is this production-ready?
The workflow is based on a real knowledge base with 94 articles and 99 sources maintained daily since April 2026. The repo includes examples, templates, and a design spec.
Design Boundaries
Deliberately not built, after three months of production logs and a survey of the ecosystem (LLM Wiki v2, llm-wiki-compiler, OKF, agent-memory literature):
- Source-hash freshness tracking — raw/ is immutable, so hashes guard against events that cannot happen. Genuinely new information arrives as new sources through normal ingest.
- Persisted line-number citations — every observed fidelity error was "value absent from the source", which a whole-file grep catches. Anchors only disambiguate a failure mode that has not occurred, and the annotation friction makes agents skip the rule.
- Numeric confidence or quality scores — false precision with no calibration behind it. Evidence strength belongs in the prose.
- Per-article review dates — nobody can predict at compile time how fast a domain moves. Maintenance is driven by whole-wiki lint, not per-page timers.
- Access-based decay — frequently asked is not the same as true.
- Retract / bad-source machinery — has not happened yet. Handle it manually until it does.
- Automatic hooks and scheduled runs — those belong to the agent harness, not a tool-agnostic skill.
- Vector or graph search — at 50K–100K tokens of curated wiki, grep and read are more reliable. Add search tooling only when recall measurably degrades.
- Typed relationship ontologies — link semantics live in the prose around the link.
- OKF conformance — the spec is a v0.1 draft with a minimal tooling ecosystem. Tracked; will be revisited.
- MCP servers, UIs, output subsystems — outside the boundary of a tool-agnostic skill.
Inspired By
Unofficial community implementation of the workflow from Karpathy's LLM Wiki idea. The value here is the reusable workflow, prompt structure, and battle-tested knowledge-compilation rules.
See also: lucasastorian/llmwiki, atomicmemory/llm-wiki-compiler. We are tracking Google's Open Knowledge Format draft and will evaluate compatibility once the spec and tooling mature.
