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. Recommended on a big catalogue where every unknown model scores the same in routing, or when using OpenAI which lists dozens of models. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if the endpoint requires one (e.g. OpenAI, DeepSeek, Groq, OpenRouter). | |
| HOUTINI_LM_THINKING | No | Thinking mode: `auto` (default) switches thinking off for models detected as supporting the toggle, `off` forces thinking off on every call (needed when a backend serves a thinking model under a name detection can't recognise), and `on` forces thinking on (worth it for bug-hunting or checking an argument, at the cost of time and tokens). | auto |
| HOUTINI_LM_SERIALISE | No | Set to 0 to turn off serialising calls (calls are queued one at a time by default, because a single GPU can only serve one request anyway). OpenRouter skips the queue, and for OpenAI, a router or a batching backend like vLLM you can turn it off with HOUTINI_LM_SERIALISE=0. | 1 |
| HOUTINI_LM_MIN_TOKENS | No | Floor for the output token cap. MCP clients habitually pass tiny caps like 256 that strangle reasoning models mid-thought, so anything under 4,096 is ignored unless you set HOUTINI_LM_MIN_TOKENS=0. | 4096 |
| HOUTINI_LM_STRUCTURED | No | Set to 1 and each inference result also carries a structuredContent block (the answer, model, tokens, timing, quality flags) to read as JSON. Leave it off for Claude Code. | 0 |
| HOUTINI_LM_ENDPOINT_URL | No | The URL of the OpenAI-compatible endpoint. Defaults to localhost:1234 where LM Studio listens. Point it at OpenAI, a LiteLLM router, OpenRouter, or another cloud API as needed. | 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