seaosinc/mcp-llm-offload

Claude の軽量な LLM 作業(要約・分類・抽出・簡単な質問)を、ローカルモデルや任意の OpenAI 互換プロバイダ(LM Studio・Ollama・OpenRouter・Grok・OpenAI・Groq・Together…)へオフロードする MCP サーバー | MCP server that offloads light LLM work (summarize, classify, extract, quick asks) from Claude to a local model or any OpenAI-compatible provider — LM Studio, Ollama, OpenRouter, Grok, OpenAI, Groq, Together…

0Stars on the repository
2Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

llm-offloader

01

seaosinc/mcp-llm-offload

Agent

A routing agent that sends lightweight text tasks to cheaper models, such as local language models, to save the main model’s usage budget.

not rated 0 2mo ago A 153 tokens original MIT

mid-tier

02

seaosinc/mcp-llm-offload

Agent

A role guide for a mid-level coding agent that handles moderate, low-risk work such as drafts, light analysis, routine code, and straightforward refactoring. It runs on Sonnet and leaves architecture, security, and highly accuracy-sensitive work to the main agent.

not rated 0 2mo ago A 187 tokens original MIT