Houtini LM
by Kerstin59718
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOUTINI_LM_MODEL | No | Pin a specific model for routing, e.g. gpt-5.2. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if needed (e.g. sk-... for OpenAI). | |
| HOUTINI_LM_THINKING | No | Controls thinking: auto (default), off, or on. | auto |
| HOUTINI_LM_SERIALISE | No | Set to 0 to disable serial request queueing for OpenAI, a router, or a batching backend like vLLM. Calls are queued one at a time by default. | 1 |
| HOUTINI_LM_MIN_TOKENS | No | Minimum output token floor; defaults to 4096. Set to 0 to allow smaller caps. | 4096 |
| HOUTINI_LM_STRUCTURED | No | Set to 1 to include a structuredContent block in inference results. | 0 |
| HOUTINI_LM_ENDPOINT_URL | No | The OpenAI-compatible endpoint URL. Defaults to LM Studio at localhost:1234. Set to e.g. http://192.168.1.50:1234 or https://api.openai.com. | 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