houtini-lm MCP Server
houtini-ai/houtini-lm
[](https://agentrank-ai.com/tool/houtini-ai--houtini-lm/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) 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.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
houtini-ai/houtini-lm is a TypeScript MCP server licensed under Apache-2.0. 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. Topics: ai-agents, claude-mcp, code-generation, developer-tool, developer-tools, lm-studio, local-llm, mcp, mcp-client, mcp-server, vibe-coding-assistant, lm-studio-mcp, openai-api, ollama, claude, model-context-protocol, token-savings, vllm.
Ranked #386 out of 24846 indexed tools.
In the top 2% of all indexed tools.
Ecosystem
Score Breakdown
121 stars → growing community
Last commit 9d ago → recently updated
15/15 issues closed → responsive maintainer
4 contributors → small team
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Badge all embed codes →
[](https://agentrank-ai.com/tool/houtini-ai--houtini-lm/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/houtini-ai--houtini-lm/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/houtini-ai--houtini-lm" alt="AgentRank"></a> Matched Queries
From the README
<div align="center">
</div>
# Houtini LM (@houtini/lm) - Offload Work from Claude Code to a Local LLM, OpenAI GPT-5/6, a Router or a Cheaper Cloud Model
**Houtini LM is an MCP server that lets Claude (or any MCP client) hand bounded work to another model - a local LLM on your GPU, OpenAI's latest GPT models, a LiteLLM router, OpenRouter or a cheap cloud API - while you carry on working in the AI platform you already like. It cuts your token bill, and it gives you a second model to review your code whenever you want one.**
<p align="center">
<a href="https://glama.ai/mcp/servers/@houtini-ai/lm">
</a>
</p>
> **Quick Navigation**
>
> [What's new](#whats-new-in-33) | [Why use it](#why-use-houtini-lm) | [Install](#install) | [How it handles different models](#how-houtini-lm-handles-different-models) | [What to hand over](#what-to-hand-over) | [Tools](#the-tools) | [Reading the footer](#reading-the-footer) | [Configuration](#configuration) | [Endpoints](#compatible-endpoints) Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.