A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed.
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.
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/SamurAIGPT/llm-wiki-agent && cp llm-wiki-agent/*.md ~/.claude/agents/Subagents overview
What people ask about llm-wiki-agent
What is SamurAIGPT/llm-wiki-agent?
+
SamurAIGPT/llm-wiki-agent is subagents for the Claude AI ecosystem. A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads them, extracts knowledge, and maintains a persistent interlinked wiki. Works with Claude Code, Codex, OpenCode, Gemini CLI. No API key needed. It has 3.5k GitHub stars and its last recorded update is dated 2026-09-08.
How do I install llm-wiki-agent?
+
You can install llm-wiki-agent by cloning the repository (https://github.com/SamurAIGPT/llm-wiki-agent) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is SamurAIGPT/llm-wiki-agent safe to use?
+
Our security agent has analyzed SamurAIGPT/llm-wiki-agent and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains SamurAIGPT/llm-wiki-agent?
+
SamurAIGPT/llm-wiki-agent is maintained by SamurAIGPT. The last recorded GitHub activity is dated 2026-09-08, with 4 open issues.
Are there alternatives to llm-wiki-agent?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy llm-wiki-agent to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/samuraigpt-llm-wiki-agent)<a href="https://claudewave.com/repo/samuraigpt-llm-wiki-agent"><img src="https://claudewave.com/api/badge/samuraigpt-llm-wiki-agent" alt="Featured on ClaudeWave: SamurAIGPT/llm-wiki-agent" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.