Llm Wiki

Lets Claude query your local LLM Wiki desktop app over its HTTP API at 127.0.0.1:19828. You say "what does my wiki say about X" or "search my knowledge base for Y" and it hits the search endpoint, reads markdown pages, and cites paths. Only triggers when you explicitly mention "LLM Wiki," "my wiki," or "知识库," so it won't fire on generic "search my notes" requests meant for Obsidian or Notion. It's read-only except for source rescans, supports hybrid keyword-vector search, and respects whatever project is open in the desktop UI via the "current" shorthand. The auth is localhost-only with a bearer token from Settings. Treat it like a private knowledge graph you've been curating that Claude can now read and ground answers in.

skills.sh installs: 1.9K
GitHub stars: 155
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add nashsu/llm_wiki_skill --skill llm-wiki --agent claude-code

Installs into .claude/skills of the current project.

Files

LLM Wiki Local API Skill

Talk to the user's locally-running LLM Wiki app over its built-in HTTP API. This is a standard JSON API — call it directly with whatever HTTP tool is already in your environment (curl, fetch, requests, http middleware, etc.). No client library to install, no SDK to learn.

Treat the wiki as a private, structured knowledge base the user has been curating: pages live as wiki/**.md, raw documents under raw/sources/, wikilinks form a graph.