AdYour product here, seen by people installing AI tools every day
AI Plugin Index
Sponsor slots open: 12 of 12, from $249 a month

How to install Memory in Gemini CLI

Gemini CLI was replaced by Antigravity CLI in June 2026. On an enterprise licence or paid API key you can still install Memory by running "gemini mcp add memory npx -y @ai-devkit/memory", then type /mcp to check it.

Built from the published package · server updated 3 days ago

  1. 1

    Run the install command

    In a terminal, run:

    gemini mcp add memory npx -y @ai-devkit/memory
  2. 2

    Check it

    Inside Gemini CLI, type /mcp to list servers and tools.

MCP servers run with your permissions. If Memory needs an API key, add it under env in the config. Check its README.

Install Memory in another app

Claude CodeClaude DesktopCursor VS CodeWindsurf Codex Antigravity CLI ChatGPT

Similar servers

Codebase MemoryDeusData
94

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

AAA Local 47k
ha-mcphomeassistant-ai
94

Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.

AAA Local 5.1k
Pi MCP earendil-works
94

Standalone Model Context Protocol client for pi and other applications

AAA Local 1380k/wk

Questions

Does Memory work in Gemini CLI?

Yes. Gemini CLI supports local and remote mcp servers, extensions (legacy), and Memory installs with the steps above.

Memory does not show up in Gemini CLI. What now?

Restart Gemini CLI fully, check the JSON is valid, and make sure Node.js (for npx) is installed. See common MCP errors and fixes.

Is Memory safe?

It scores 89 of 100. Review the code before you install it, and only give it the access it needs. Grades and details.