houtini-ai/lm
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 claude decide what work to assign and why.
This tool helps software developers reduce their cloud LLM costs when using Claude Code for large programming tasks. It automatically routes routine coding chores, like generating test stubs or commit messages, to a local, free LLM server. Claude continues to handle complex architectural planning, while the local model takes care of the grunt work, saving you significant token expenses.
Use this if you are a software developer frequently using Claude Code for extensive refactoring, code reviews, or generating boilerplate, and want to lower your cloud API costs.
Not ideal if you primarily use Claude for small, quick questions or tasks that don't involve reading and analyzing large code files, as the overhead may outweigh the token savings.
Stars
12
Forks
5
Language
JavaScript
License
MIT
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/houtini-ai/lm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.