Skip to content
Grok

Orma Memory for Grok

io.github.wizardwithcodehazard/orma

Episode-first, zero-latency long-term memory for local LLMs and AI coding assistants.

client:Grok transport:stdio runtime:pypi

Install Orma Memory in Grok

.mcp.json (in your project root)

{
  "mcpServers": {
    "orma": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "orma-ai"
      ]
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

Orma Memory in other clients