# houtini-lm

> houtini-lm — houtini-ai-houtini-lm. Use this tool when you need to optimize Claude Code token usage by offloading tasks to local or cloud Large Language Models (LLMs). The houtini-lm MCP server solves token management problems by delegating bounded tasks, integrating with platforms like LM Studio and DeepSeek. It accepts code tasks as input and returns processed outputs, ideal for use cases involving multiple LLMs and Git version control.

Canonical page: https://skillsregistry.net/skills/houtini-ai-houtini-lm  
JSON: https://api.skillsregistry.net/v1/skills/houtini-ai-houtini-lm

## Description

MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.

## Trust

- **Trust score (0–1):** 0.76
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/houtini-ai/houtini-lm)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "houtini-ai-houtini-lm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/houtini-ai-houtini-lm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/houtini-ai-houtini-lm/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt