mindbase — security grade SAFE, quality 51/100

Security audit verdict: SAFE · quality 51/100

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 frankchu91 · MCP Server · ★ 68

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is mindbase safe to install? View the security audit →

About mindbase

MindBase — Karpathy's LLM Wiki, as a product An open-source implementation of Andrej Karpathy's LLM Wiki idea: an AI that builds and maintains a wiki from your sources. Not RAG-in-a-vector-DB. A real markdown wiki on your disk, that an LLM gardens for you between conversations. One command: starts the local server, opens the web app, and walks you through picking a free local model that fits your RAM. No API key, nothing leaves your machine. (Node 20+) MindBase implements Andrej Karpathy's [LLM-Wiki pattern](https://x.com/karpathy/s

aikarpathyknowledge-basellmllm-wikillm-wiki-karpathyllm-wiki-knowledge-basellm-wiki-mcpllm-wiki-patternllm-wiki-personal-knowledge-base

Quick Facts

Stars68
Forks11
LanguageTypeScript
CategoryMCP Server
LicenseMIT
Quality Score51.4750320266457/100
Last Updated2026-08-16
Created2026-04-26
Platformsbrowser, mcp, node
Est. Tokens~13k

Compatible Skills

These tools work well together with mindbase for enhanced workflows:

  • llm-wiki-plugin — semantic(0.52)+complementary+rare_topics+same_lang+similar_pop+shared_platform (73%)
  • obsidian-llm-wiki — semantic(0.48)+complementary+rare_topics+same_lang+similar_pop+shared_platform (71%)
  • open-knowledge — semantic(0.62)+complementary+rare_topics+same_lang+shared_platform (66%)

mindbase alternative? Top 6 similar tools

Looking for a mindbase alternative? If you're comparing mindbase with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • LLM-Wiki by Oshayr · ⭐ 51

    Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked

  • matryca-plumber by MarcoPorcellato · ⭐ 98

    Local-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edi

  • Kompl by tuirk · ⭐ 76

    A compounding LLM-wiki, best fit as a personal second brain that organizes and updates itself as it grows, zer

  • mcp-server-atlassian-confluence by aashari · ⭐ 61

    Node.js/TypeScript MCP server for Atlassian Confluence. Provides tools enabling AI systems (LLMs) to list/get

  • ChatCrystal by ZengLiangYi · ⭐ 58

    Local-first AI PKM for coding conversations: import Claude Code/Cursor/Codex, distill notes, semantic search,

  • mcp-server by strands-agents · ⭐ 293

    This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is mindbase?

mindbase is Karpathy's LLM Wiki idea as a product — an AI that builds and maintains a markdown wiki from your notes and sources. MCP server + web UI, runs on free local models (Ollama), no API key needed. MIT.. It is categorized as a MCP Server with 68 GitHub stars.

What programming language is mindbase written in?

mindbase is primarily written in TypeScript. It covers topics such as ai, karpathy, knowledge-base.

How do I install or use mindbase?

You can find installation instructions and usage details in the mindbase GitHub repository at github.com/frankchu91/mindbase. The project has 68 stars and 11 forks, indicating an active community.

What license does mindbase use?

mindbase is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to mindbase?

The top alternatives to mindbase on Agent Skills Hub include LLM-Wiki, matryca-plumber, Kompl. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse MCP Server tools