by houtini-ai · MCP Server · ★ 71
@houtini/lm Houtini LM - Save Tokens by Offloading Tasks from Claude Code to Your Local LLM Server (LM Studio / Ollama) or a Cloud API Quick Navigation How it works Developer guide I built this because I kept leaving Claude Code running overnight on big refactors and the token bill was painful. A huge chunk of that spend goes on bounded tasks any decent model handles fine - generating boilerplate, code review, commit messages, format conversion. Stuff that doesn't need Claude's reasoning or tool
| Stars | 71 |
| Forks | 14 |
| Language | JavaScript |
| Category | MCP Server |
| License | MIT |
| Quality Score | 57.388/100 |
| Last Updated | 2026-04-21 |
| Created | 2025-09-04 |
| Platforms | claude-code, cli, mcp, node |
| Est. Tokens | ~85k |
These tools work well together with houtini-lm for enhanced workflows:
Explore other popular mcp server tools:
houtini-lm is 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.. It is categorized as a MCP Server with 71 GitHub stars.
houtini-lm is primarily written in JavaScript. It covers topics such as ai-agents, claude, claude-mcp.
You can find installation instructions and usage details in the houtini-lm GitHub repository at github.com/houtini-ai/houtini-lm. The project has 71 stars and 14 forks, indicating an active community.
houtini-lm is released under the MIT license, making it free to use and modify according to the license terms.