houtini-ai/houtini-lm

Local or Cloud LLM support via MCP for your AI assistant with Houtini-LM - uses OpenAPI API for LM Studio, Cloud API 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.

42
/ 100
Emerging

Implements intelligent task delegation between Claude and local/cloud LLMs via MCP, using HuggingFace metadata enrichment to automatically profile model capabilities and route work appropriately. Achieves 86-95% token savings on file-heavy tasks by keeping source code out of Claude's context window while delegating bounded work (code review, boilerplate, format conversion) to cheaper inference endpoints. Supports LM Studio, Ollama, vLLM, and OpenAI-compatible APIs with zero-friction setup through stdio transport and automatic model discovery via cached SQLite profiles.

No Package No Dependents
Maintenance 13 / 25
Adoption 5 / 25
Maturity 9 / 25
Community 15 / 25

How are scores calculated?

Stars

13

Forks

5

Language

JavaScript

License

MIT

Last pushed

Mar 14, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/houtini-ai/houtini-lm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.