Skip to content
mcp/harbor
Gemini CLI

lm for Gemini CLI

io.github.houtini-ai/lm

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

client:Gemini CLI transport:stdio runtime:npm

Install lm 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": {
    "lm": {
      "command": "npx",
      "args": [
        "-y",
        "@houtini/lm"
      ],
      "env": {
        "HOUTINI_LM_ENDPOINT_URL": "<HOUTINI_LM_ENDPOINT_URL>",
        "HOUTINI_LM_API_KEY": "<HOUTINI_LM_API_KEY>",
        "HOUTINI_LM_MODEL": "<HOUTINI_LM_MODEL>",
        "HOUTINI_LM_PROVIDER": "<HOUTINI_LM_PROVIDER>"
      }
    }
  }
}

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

lm in other clients

lm MCP server