wikix

🇺🇸 English · 🇨🇳 简体中文 · 🇯🇵 日本語 · 🇰🇷 한국어

An LLM-maintained personal wiki — a persistent, compounding second brain you curate while the agent does the bookkeeping.

Based on Karpathy's LLM Wiki pattern (original gist · local copy). You drop sources into raw/, the agent ingests them into a structured wiki/ of summaries, concept pages, entities, and syntheses — updating cross-references and flagging contradictions as the knowledge base grows.

Quick Start

1. Clone this repo and open it in Claude Code, Codex, OpenCode, Hermes, or OpenClaw.

   Copyable CLI example:

   git clone https://github.com/CaoYuhaoCarl/wikix.git
   cd wikix
   
   claude ## Change to codex, opencode, hermes, or openclaw if needed
   

2. Drop a source file into raw/ (a markdown article, paper, PDF, transcript, PNG/JPG image, etc.). The directory is committed with a placeholder, but your source files stay local by default.

3. Paste this prompt:

   You're now my LLM wiki agent. Read AGENTS.md (Codex/Opencode/Hermes/Openclaw) or CLAUDE.md (Claude Code)
   for the operating schema. Ingest the new file in raw/ following the ingest
   workflow, then update index.md and log.md.
   

4. Browse the generated pages in wiki/. After each ingest, open the repo in
   Obsidian to inspect the knowledge graph; the smoother
   path is to install the community Claudian plugin and launch Claude Code,
   Codex, or OpenCode directly from Obsidian. That lets you ingest, query, and
   lint while watching the graph update live.

   

Starting from scratch in a different project? Copy AGENTS.md, meta/templates/, and meta/karpathy-llm-wiki.md into an empty directory, then ask your agent: "Implement this idea file as my second brain. Set up the schema, index.md, log.md, and folder conventions."

Structure

raw/         # local-only immutable source documents; only .gitkeep is committed
wiki/        # LLM-generated knowledge layer
  sources/   # one note per ingested raw source
  concepts/  # reusable topic pages
  entities/  # people, orgs, projects, tools
  syntheses/ # cross-source analysis & conclusions
  questions/ # saved answers to important questions
meta/        # methodology, design notes, page templates
index.md     # content catalog (read first on every query)
log.md       # append-only chronological activity log
AGENTS.md    # operating schema for Codex
CLAUDE.md    # operating schema for Claude Code (mirror of AGENTS.md)

Workflows

The agent follows three core workflows defined in AGENTS.md:

• Ingest — read a new raw/ source, discuss takeaways, then write a source note plus any new/updated concept, entity, or synthesis pages.
• Query — answer a question by reading index.md first, then drilling into relevant wiki pages; save durable answers back to wiki/questions/.
• Lint — health-check the wiki for orphans, broken links, contradictions, stale claims, and missing pages.

Conventions

• Files and folders use lowercase kebab-case.
• Every wiki page has YAML frontmatter (title, type, created, updated, sources, tags).
• Raw sources are immutable. The agent never edits files in raw/.
• The agent aligns with you on emphasis and scope before writing.

See AGENTS.md for the full schema, workflow rules, and evidence rules. Page templates live in meta/templates/.

Credits

Pattern by Andrej Karpathy — original gist (local copy at meta/karpathy-llm-wiki.md).

Thanks also to Obsidian for the local knowledge graph experience, and Claudian for making the agent workflow available directly inside Obsidian.

License

MIT — covers the schema, templates, and tooling in this repository (AGENTS.md, CLAUDE.md, README*.md, meta/, etc.).

Note: files you place in raw/ keep their original licenses and are ignored by Git by default; only raw/.gitkeep is committed so the folder exists after cloning. Pages the agent generates in wiki/ are derivative works of those sources and inherit their license obligations. If you publish generated wiki pages, vet the corresponding local sources and license terms accordingly.