Houtini LM
by nBarbieri34
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOUTINI_LM_MODEL | No | Pin the model to use. On a big catalogue every unknown model scores the same and the first listed wins, so pin one (for example gpt-5.2). Can also be passed as the `model` parameter on an individual call. | |
| HOUTINI_LM_API_KEY | No | API key for the endpoint, if the endpoint needs one (for example an OpenAI key like sk-...). | |
| HOUTINI_LM_THINKING | No | Controls thinking/reasoning. `auto` (default) switches thinking off for models detected as supporting the toggle (Qwen3, Gemma 4, Nemotron, DeepSeek R1, GLM-4, gpt-oss). `off` forces that on every call. `on` forces thinking on, at the cost of time and tokens. | auto |
| HOUTINI_LM_SERIALISE | No | 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 | Minimum output token floor. 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 HOUTINI_LM_STRUCTURED=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, which shows the model only that block when it's present. | 0 |
| HOUTINI_LM_ENDPOINT_URL | No | The URL of the OpenAI-compatible endpoint to delegate to (LM Studio, Ollama, vLLM, SGLang, a LiteLLM router, or a cloud API such as OpenAI). LM Studio listens on localhost:1234 by default, which is where houtini-lm looks first. | 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