Houtini LM
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOUTINI_LM_MODEL | No | Pin a specific model to use, useful on large catalogues where every unknown model scores the same. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if it needs one. | |
| HOUTINI_LM_THINKING | No | Controls thinking mode: auto (default), off, or on. | |
| HOUTINI_LM_SERIALISE | No | Set to 0 to turn off serialisation/queuing of calls (useful for OpenAI, a router, or a batching backend like vLLM). | |
| HOUTINI_LM_MIN_TOKENS | No | Set to 0 to disable the minimum output token floor (anything under 4,096 is ignored by default unless this is set to 0). | |
| HOUTINI_LM_STRUCTURED | No | Set to 1 to include a structuredContent block in each inference result for use from your own scripts. | |
| HOUTINI_LM_ENDPOINT_URL | No | The URL of the OpenAI-compatible endpoint (e.g. a local LM Studio instance, Ollama, vLLM, SGLang, a LiteLLM router, or a cloud API). Defaults to 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
ResponsivenessResponsive