cortex

Gustav-Proxi/cortex

★ 0 stars Swift 🧠 Memory/Knowledge Updated today

Local-first MCP server giving any LLM client semantic + literal search and full read/write over an Obsidian/markdown vault. Local embeddings via Ollama, sqlite-vec index.

View on GitHub → Try with Claude — $10 free →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "cortex": {
      "command": "npx",
      "args": [
        "-y",
        "Gustav-Proxi/cortex"
      ]
    }
  }
}

README Excerpt

<div align="center"> **The local-first brain for your notes — one MCP server that gives every LLM client your entire Obsidian vault.** </div> > **"Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase."** > — Andrej Karpathy, [*LLM Wiki*](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) (2026)

Tools (8)

CORTEX_ALLOW_EXECCORTEX_DBCORTEX_EMBED_DIMCORTEX_EMBED_MODELCORTEX_EXEC_TIMEOUTCORTEX_HTTP_API_PORTCORTEX_VAULTOLLAMA_HOST

Topics

knowledge-basellmmcpmodel-context-protocolobsidianollamaragsecond-brainsemantic-searchsqlite-vec

cortex

Quick Install

README Excerpt

Tools (8)

Topics

Related Memory/Knowledge Servers