Wiki Graph — AI skill for Claude Code
Build the LLM Wiki knowledge graph.
How to install Wiki Graph
Installs to ~/.claude/commands/samuraigpt-llm-wiki-agent-wiki-graph.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/SamurAIGPT/llm-wiki-agent/HEAD/.claude/commands/wiki-graph.md -o ~/.claude/commands/samuraigpt-llm-wiki-agent-wiki-graph.md Restart Claude Code, or start a new session, for it to be picked up.
What Wiki Graph does
Build the LLM Wiki knowledge graph.
Usage: /wiki-graph
First try running: python tools/build_graph.py --open
If that fails (missing dependencies), build the graph manually:
- Use Grep to find all [[wikilinks]] across every file in wiki/
- Build a nodes list: one node per wiki page, with id=relative-path, label=title, type from frontmatter
- Build an edges list: one edge per [[wikilink]], tagged EXTRACTED
- Infer additional implicit relationships between pages not captured by wikilinks —
Alternatives in AI
- WeKnora — Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, an 26.9k ★
- Open Knowledge — Beautiful, AI-native markdown IDE and LLM wiki 3.7k ★
- Karpathy LLM Wiki — Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex 618 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
MeMex Zero RAG
The Karpathy LLM Wiki, production-ready. Zero-RAG personal knowledge base with MCP server, multi-agent support
TencentDB Agent Memory
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into f
Graqle
Persistent organisational intelligence for AI agents. Turn codebases, documents, policies and decisions into a
Capy Cortex
Autonomous memory and learning system for AI coding agents. LLM-powered knowledge extraction, triple fusion re
LLM Kernel
Rust foundation library for AI-native apps — 16-provider catalog, async LLM client, MCP server, knowledge grap
Codetospec
Turn a legacy codebase into a verifiable, versionable knowledge graph of its business rules — LLM map/reduce i
Related Agents
Triage TS
LLM instruction for the TypeScript orchestrator triage role. Receives a task description, project structure sn
Kg Extractor
Schema-guided knowledge-graph extractor. Reads batches of text chunks (KIPs, issue descriptions, comments) and
Second Brain Curator
Maintains the user's Obsidian "second brain" vault (Karpathy LLM-Wiki pattern) and its ingest pipeline — runs/