#3939th of 60 in RAG, knowledge and search
llm-wiki-agent
Coding-agent skill that builds an interlinked markdown wiki from ingested documents
- Stars
- 3.7k
- License
- MIT
- Last commit
- Nov 2026
- Language
- Python
2,199 on 22 Apr 20263,693 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A set of schema files (CLAUDE.md, AGENTS.md, GEMINI.md) and Claude Code slash commands that make a coding agent ingest documents from raw/ into a markdown wiki with source, entity, concept and synthesis pages. It also lints for orphans and contradictions, and builds a vis.js graph.html from wikilinks plus agent-inferred edges. Non-markdown files are converted with markitdown.
Who it is for: Researchers and note-takers using a coding agent who want a self-maintained wiki
Strengths
- Output is plain markdown in a git repo, browsable in Obsidian
- Works with Claude Code, Codex, OpenCode and Gemini CLI via per-agent schema files
- Flags contradictions at ingest and lints for orphans and broken links
- Graph build is SHA256-cached and outputs a self-contained graph.html, no server
Weaknesses
- Requires a separate coding agent; the skill does nothing on its own
- Standalone tools/ scripts need ANTHROPIC_API_KEY; no other provider is documented
- Wiki quality depends on the agent's reading; no accuracy figures given
- No published release and no multi-user or web UI
What it needs
- no GPU
- Needs Claude Code, Codex, OpenCode or Gemini CLI, markitdown, NetworkX, ANTHROPIC_API_KEY (standalone tools/ scripts)
- Models: Claude, Codex, Gemini CLI
Also in RAG, knowledge and search
See all 60| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | Open NotebookSelf-hosted NotebookLM alternative for research notebooks, chat, and podcasts | 90 out of 100 |
| 3 | LightRAGGraph-based RAG framework with a REST server and WebUI | 90 out of 100 |
| #4 | deeptutorTutoring workspace with knowledge bases, guided learning, memory and quizzes | 89 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 89 out of 100 |