Home › Other › houtini-lm

houtini-lm

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

TypeScript

★ 119 stars Last pushed 2026-09-24 License: Apache-2.0

View repository →

Connect

Review any command before running it. Package names and URLs come from the server's own registry entry.

Package (npm 3.3.3)

npx -y @houtini/[email protected]

Or add to your MCP client config:

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

HOUTINI_LM_ENDPOINT_URL — Base URL of the OpenAI-compatible API endpoint (e.g. http://localhost:1234, https://openrouter.ai/api). Legacy alias: LM_STUDIO_URL.
HOUTINI_LM_API_KEY secret — Bearer token for API authentication (no auth if blank). Legacy aliases: LM_STUDIO_PASSWORD, LM_PASSWORD, OPENROUTER_API_KEY.
HOUTINI_LM_MODEL — Model identifier to use for requests (auto-detected if not set). Legacy alias: LM_STUDIO_MODEL.
HOUTINI_LM_PROVIDER — Optional provider override: 'openrouter' forces OpenRouter-specific handling (attribution headers, reasoning.exclude, no inference serialisation). Auto-detected from the endpoint URL when possible.