No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by SamurAIGPT · Codex Skill · ★ 3.5k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is llm-wiki-agent safe to install? View the security audit →
Featured in: Personal Knowledge Skills · Obsidian, Second Brain & LLM Wiki
LLM Wiki Agent A coding agent skill. Drop source documents into and type — the agent reads them, extracts knowledge, and builds a persistent interlinked wiki. Every new source makes the wiki richer. You never write it. Most knowledge tools make you search your own notes. This one reads everything you've collected and writes a structured wiki that compounds over time — cross-references already built, contradictions already flagged, synthesis already done. Install Requires: Claude Code, Codex, Gemini CLI, or any agent that reads a config file. bash git clone https://github.com/SamurAIGPT/llm-wiki-agent.git cd llm-
| Stars | 3,548 |
| Forks | 407 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 72.1434620621838/100 |
| Open Issues | 4 |
| Last Updated | 2026-09-21 |
| Created | 2023-04-21 |
| Platforms | claude-code, cli, codex, gemini, python |
| Est. Tokens | ~15k |
Looking for a llm-wiki-agent alternative? If you're comparing llm-wiki-agent with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files
Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with A
Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Sto
TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c
Give Claude Code, Cursor, Codex CLI a ChatGPT for your codebase. Multi-agent knowledge engine, grounded Q&A wi
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, ope
Explore other popular codex skill tools:
llm-wiki-agent is 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 Co. It is categorized as a Codex Skill with 3.5k GitHub stars.
llm-wiki-agent is primarily written in Python. It covers topics such as ai-agent, ai-tools, automation.
You can find installation instructions and usage details in the llm-wiki-agent GitHub repository at github.com/SamurAIGPT/llm-wiki-agent. The project has 3.5k stars and 407 forks, indicating an active community.
llm-wiki-agent is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to llm-wiki-agent on Agent Skills Hub include claude-obsidian, note-gen, obsidian-second-brain. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: