Skip to content
mcp/harbor
Gemini CLI

agent memory os for Gemini CLI

io.github.yamantaka520/agent-memory-os

Local-first memory engine for AI-agent teams: team/project ACL, recall, and federated sync.

client:Gemini CLI transport:stdio runtime:pypi

Install agent memory os in Gemini CLI

~/.gemini/settings.json · windows: %USERPROFILE%\.gemini\settings.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "agent-memory-os": {
      "command": "uvx",
      "args": [
        "agent-memory-os"
      ],
      "env": {
        "AGENT_MEMORY_AGENT_ID": "<AGENT_MEMORY_AGENT_ID>",
        "AGENT_MEMORY_HOME": "<AGENT_MEMORY_HOME>"
      }
    }
  }
}

Gemini expands $VAR and ${VAR} inside env values, so a secret can live in your shell rather than this file. Gemini CLI docs

agent memory os in other clients

agent memory os MCP server