llm-wiki-agent

LLM Wiki Agent is a Python-based coding agent skill that automates the construction and maintenance of a personal wiki from source documents. Users drop files into a `raw/` directory and issue ingest commands; the agent reads each document, extracts entities, concepts, and key ideas, then writes and cross-references structured Markdown pages under a `wiki/` directory with subdirectories for sources, entities, concepts, and syntheses. It also generates an interactive knowledge graph (`graph.html`) using vis.js, with community detection clustering related topics and dotted edges representing inferred implicit relationships. A standout feature is contradiction flagging at ingest time rather than query time, and a lint command that identifies orphan pages and suggests missing sources. The tool integrates directly with Claude Code via dedicated slash commands (`/wiki-ingest`, `/wiki-query`, `/wiki-lint`, `/wiki-graph` defined in `.claude/commands/`), and also supports Codex, OpenCode, and Gemini CLI through agent-specific config files. No API key or Python setup is required. Researchers, students, and anyone building a long-term knowledge base across formats including PDF, DOCX, EPUB, and PPTX will find it useful.

Lo que la gente pregunta sobre llm-wiki-agent