crit for Gemini CLI

io.github.crit-labs/crit

Build, evaluate and serve a bespoke LLM inference engine for your own GPU with crit's commands.

client:Gemini CLI transport:stdio runtime:pypi

Install crit in Gemini CLI

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

{
  "mcpServers": {
    "crit": {
      "command": "uvx",
      "args": [
        "crit"
      ]
    }
  }
}

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