by houtini-ai · MCP 服务器 · ★ 11
@houtini/lm Houtini LM - Save Tokens by Offloading Tasks from Claude Code to Your Local LLM Server (LM Studio / Ollama), Openrouter 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 reason
| Stars | 11 |
| Forks | 5 |
| Language | JavaScript |
| Category | MCP 服务器 |
| License | MIT |
| Quality Score | 37.3/100 |
| Open Issues | 2 |
| Last Updated | 2026-03-10 |
| Created | 2025-09-04 |
| Platforms | claude-code, cli, mcp, node |
| Est. Tokens | ~93k |
These tools work well together with lm for enhanced workflows:
Explore other popular mcp 服务器 tools:
lm is Offload Tasks from Claude to your Local LLM With Houtini-LM - uses OpenAPI for LM Studio and Ollama Compatibility. Save tokens by offloading some grunt work for your API - our tool description helps c. It is categorized as a MCP 服务器 with 11 GitHub stars.
lm is primarily written in JavaScript. It covers topics such as ai-agents, claude-mcp, code-generation.
You can find installation instructions and usage details in the lm GitHub repository at github.com/houtini-ai/lm. The project has 11 stars and 5 forks, indicating an active community.
lm is released under the MIT license, making it free to use and modify according to the license terms.