obsidian-wiki MCP Server
Ar9av/obsidian-wiki
[](https://agentrank-ai.com/tool/Ar9av--obsidian-wiki/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
Ar9av/obsidian-wiki is a Python tool licensed under MIT. Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents Topics: agent-skills, knowledge-base, llm-tools, obsidian, wiki, brain, obsidian-brain, knowledge-graph, memory, agent-memory, claude-code, claude-skills, codex, karpathy, llm-wiki, mcp, pkm, second-brain.
Ranked #238 out of 24846 indexed tools.
In the top 1% of all indexed tools.
Has 3,554 GitHub stars.
Has 33 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
3,554 stars → well-known project
Last commit 7d ago → actively maintained
79/85 issues closed → responsive maintainer
33 contributors → active community
No dependents → no downstream usage
670 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
<h1 align="center">obsidian-wiki</h1> <p align="center"><b>A digital brain you grow with your AI agent.</b></p> <p align="center"> It remembers what you figure out, connects it to what you already know,<br> and answers when you ask. </p> <p align="center"> <a href="https://pypi.org/project/obsidian-wiki/"></a> <a href="https://github.com/ar9av/obsidian-wiki/pulls"></a> <a href="https://x.com/_ar9av"></a> <a href="https://discord.gg/FH2PRX754c"></a> </p> <p align="center"> </p> <p align="center"> </p> <p align="center"> English | <a href="https://github.com/Ar9av/obsidian-wiki/blob/main/README_TW.md">繁體中文</a> </p> --- You solve a hard problem on a Tuesday. Three months later, in a different repo, you solve it again from scratch — because the answer lived in a chat log you'll never find. This fixes that. Point it at a folder, tell your agent what to remember, and it compiles what you learn into interconnected markdown you own. The pattern comes from Andrej KaRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.