Houtini LM
by SagaZhu805
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOUTINI_LM_MODEL | No | Pin the model to use, e.g. gpt-5.2. Recommended for OpenAI and other large catalogues, where every unknown model scores the same and the first listed wins. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if it needs one (for example an OpenAI key when pointing HOUTINI_LM_ENDPOINT_URL at https://api.openai.com). | |
| HOUTINI_LM_THINKING | No | Controls model thinking: 'auto' (default) switches thinking off for models detected as supporting the toggle, 'off' forces thinking off on every call, 'on' forces thinking on. Use 'auto' or 'off' when Claude does the reasoning and the other model does the drafting; 'on' is worth it for bug-hunting or checking an argument. | |
| HOUTINI_LM_SERIALISE | No | Set to 0 to turn off one-at-a-time queuing of calls (used for OpenAI, a LiteLLM router or a batching backend like vLLM); a single GPU should leave the default queuing on. | |
| HOUTINI_LM_MIN_TOKENS | No | Floor for the output token budget. Anything under 4,096 is ignored unless you set this to 0. | |
| HOUTINI_LM_STRUCTURED | No | Set to 1 so each inference result also carries a structuredContent block (answer, model, tokens, timing, quality flags) for use from your own scripts. Leave off for Claude Code. | |
| HOUTINI_LM_ENDPOINT_URL | No | URL of the OpenAI-compatible endpoint to delegate work to (LM Studio, Ollama, vLLM, SGLang, a LiteLLM router, OpenRouter, OpenAI, DeepSeek and the like). Defaults to LM Studio on http://localhost:1234. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessNo issues