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 AgriciDaniel · Agent Tool · ★ 14.8k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is claude-obsidian safe to install? View the security audit →
Featured in: Obsidian, Second Brain & LLM Wiki
claude-obsidian Claude + Obsidian knowledge companion. A running notetaker that builds and maintains a persistent, compounding wiki vault. Every source you add gets integrated. Every question you ask pulls from everything that has been read. Knowledge compounds like interest. Based on Andrej Karpathy's LLM Wiki pattern. What It Does You drop sources. Claude reads them, extracts entities and concepts, updates cross-references, and files everything into a structured Obsidian vault. The wiki gets richer with every ingest. You ask questions. Claude reads the hot cache (recent context), scans the index, drills into relevant pages, and synthesizes an answer. It cites specific wiki pages, not training data. You lint. Claude finds orphans, dead links, stale claims, and missing cross-references. Your wiki stays healthy without manual cleanup. At the end of every session, Claude updates a hot cache. The next session starts with full recent context, no recap needed. Quick Start Option 1: Clone as
| Stars | 14,802 |
| Forks | 1,475 |
| Language | Python |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 69.7601337717112/100 |
| Open Issues | 20 |
| Last Updated | 2026-09-10 |
| Created | 2026-04-07 |
| Platforms | claude-code, python |
| Est. Tokens | ~16k |
These tools work well together with claude-obsidian for enhanced workflows:
Looking for a claude-obsidian alternative? If you're comparing claude-obsidian with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Persistent memory for Claude Code and 6 other CLI agents, stored as plain markdown in your Obsidian vault. Sto
A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads t
Capture first. Organize later. A local-first Markdown app that turns scattered records into clear notes with A
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, se
An Obsidian plugin that embeds Claude Code/Codex as an AI collaborator in your vault
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: htt
Explore other popular agent tool tools:
claude-obsidian is Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own. AI note-taking, personal. It is categorized as a Agent Tool with 14.8k GitHub stars.
claude-obsidian is primarily written in Python. It covers topics such as agent-skills, ai-note-taking, ai-second-brain.
You can find installation instructions and usage details in the claude-obsidian GitHub repository at github.com/AgriciDaniel/claude-obsidian. The project has 14.8k stars and 1475 forks, indicating an active community.
claude-obsidian is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to claude-obsidian on Agent Skills Hub include obsidian-second-brain, llm-wiki-agent, note-gen. 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: