Karpathy-style local-first LLM Wiki / Knowledge Compiler for Claude Code
npx claudepluginhub bradduy/wiki-knowledge-compilerKarpathy-style local-first LLM Wiki / Knowledge Compiler for Claude Code. Ingest sources, build a structured markdown knowledge base, and maintain it with AI-powered workflows.
Production-ready workflow orchestration with 79 focused plugins, 184 specialized agents, and 150 skills - optimized for granular installation and minimal token usage
Curated collection of 141 specialized Claude Code subagents organized into 10 focused categories
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations
A local-first LLM Wiki / Knowledge Compiler plugin for Claude Code.
Inspired by Karpathy's "LLM Wiki" concept: raw sources are immutable, the wiki is derived knowledge, and useful outputs are always written back.
wiki-knowledge-compiler turns Claude Code into an AI-powered knowledge management system that:
Everything is plain markdown with YAML frontmatter. No databases, no cloud services, no proprietary formats.
The easiest way to install. Open Claude Code and run:
/plugin marketplace add bradduy/wiki-knowledge-compiler
Or use the Add Marketplace dialog in Claude Code settings:
bradduy/wiki-knowledge-compilerThen install the plugin:
/plugin install wiki-knowledge-compiler@wiki-knowledge-compiler
Once installed, run /setup-wiki to configure your project size and search backend.
git clone https://github.com/bradduy/wiki-knowledge-compiler.git
cd wiki-knowledge-compiler
Open the folder in Claude Code — it will automatically detect CLAUDE.md and .claude/ configuration. All commands are immediately available.
Copy the plugin files into your repo:
git clone https://github.com/bradduy/wiki-knowledge-compiler.git /tmp/wkc
# Copy plugin structure
cp -r /tmp/wkc/.claude/ your-project/.claude/
cp -r /tmp/wkc/.claude-plugin/ your-project/.claude-plugin/
cp -r /tmp/wkc/{agents,skills,templates} your-project/
cp /tmp/wkc/CLAUDE.md your-project/CLAUDE.md
cp /tmp/wkc/wiki.config.md your-project/wiki.config.md
# Initialize the knowledge base
bash /tmp/wkc/scripts/init-kb.sh your-project/knowledge-base
# Clean up
rm -rf /tmp/wkc
After any install method, open Claude Code in the project directory and run:
/setup-wiki
This walks you through project size configuration and confirms everything is working.
| Command | Description |
|---|---|
/setup-wiki | Start here. Interactive setup — choose project size, configure search backend |
/ingest-source <path-or-url> | Add a raw source and extract knowledge from it |
/query-wiki <question> | Search the wiki, answer with citations, write back if useful |
/update-index | Rebuild all knowledge base indexes from the file system |
/health-check | Audit for orphans, duplicates, stale pages, weak links |
/generate-insights [focus] | Synthesize new insights from existing knowledge |
knowledge-base/
raw/ # Immutable source documents
concepts/ # Atomic concept pages (one per file)
topics/ # Broader topic overviews
summaries/ # Per-source summaries with provenance
insights/ # Cross-cutting observations
index/ # Auto-generated indexes
drafts/ # Work-in-progress pages
references/ # External URL/resource stubs
log.md # Append-only activity log
/ingest-source ~/papers/vaswani-2017-attention-is-all-you-need.pdf
Creates: raw copy, summary, concept pages (attention, self-attention, multi-head attention, etc.), topic updates, index updates, log entry.
/query-wiki How does self-attention differ from cross-attention?
Searches the wiki, answers with citations to specific pages, identifies knowledge gaps, and writes back the synthesis as an insight if it's novel.
/health-check
Reports: 2 orphan pages, 1 suspected duplicate (attention.md vs attention-mechanism.md), 3 summaries with broken source links. Offers to auto-fix safe issues.
/generate-insights scaling laws
Reads across all sources related to scaling, identifies cross-cutting patterns, generates insight pages with confidence ratings.