Camel-AutoGPT
LLM Wiki Agent is a coding agent skill that ingests source documents and automatically builds a persistent, interlinked wiki with entity and concept pages, cross-references, contradiction flags, and a knowledge graph. It solves the problem of knowledge management by compiling and synthesizing information from multiple sources over time, eliminating the need for manual note-taking. It is for developers and researchers who use AI coding agents like Claude Code, Codex, or Gemini CLI.
✨ Key features
- Auto-creates entity and concept pages from sources
- Flags contradictions at ingest time
- Builds interactive knowledge graph (graph.html)
- Supports multi-format ingest (PDF, DOCX, PPTX, etc.)
- Provides lint reports for gaps and orphans
- Works with Claude Code, Codex, Gemini CLI
🎯 Use cases
- Research: ingest papers and query synthesized knowledge
- Reading books: build character and theme pages
- Personal knowledge base: track journal entries and articles
- Business intelligence: analyze meeting transcripts and customer calls
- Competitive analysis: track companies and market trends
📦 Installation
git clone https://github.com/SamurAIGPT/llm-wiki-agent.git
cd llm-wiki-agent
Open in your agent — no API key or Python setup needed:
claude # reads CLAUDE.md + .claude/commands/ (slash commands available)
codex # reads AGENTS.md
opencode # reads AGENTS.md
gemini # reads GEMINI.md
🚀 Usage
ingest raw/papers/my-paper.md # ingest a markdown source
query: what are the main themes? # synthesize answer from wiki pages
lint # find orphans, contradictions, gaps
build graph # build graph.html from all wikilinks
Plain English works too:
"Ingest this paper: raw/papers/llama2.md"
"What does the wiki say about attention mechanisms?"
❓ FAQ
What file formats can I ingest?
It supports markdown, PDF, DOCX, PPTX, XLSX, HTML, TXT, CSV, JSON, XML, RST, EPUB, and more. Non-markdown files are auto-converted via markitdown.
Do I need an API key?
No, for basic use with a coding agent, no API key is needed. However, standalone Python scripts in tools/ require ANTHROPIC_API_KEY.
How does the knowledge graph work?
It builds graph.html with nodes as wiki pages and edges from wikilinks (deterministic) plus inferred relationships (semantic). It uses Louvain community detection and SHA256 caching.
Can I use it with Obsidian?
Yes, the wiki is designed to be browsed in Obsidian. You can symlink the wiki directory into your vault and use the graph view and Dataview plugin.
📊 Repository
🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.