Heratiki/locallama-mcp
An MCP Server that works with Roo Code/Cline.Bot/Claude Desktop to optimize costs by intelligently routing coding tasks between local LLMs free APIs and paid APIs.
Implements intelligent task routing through a decision engine that analyzes code complexity, dependency mapping, and execution order to minimize token costs—combining real-time API monitoring with benchmarking data from local LLMs (LM Studio, Ollama) and OpenRouter's free/paid models. Features BM25-based semantic code search via Retriv, adaptive model selection with performance history, and preemptive routing that avoids API calls for faster decisions without sacrificing accuracy.
No commits in the last 6 months.
Stars
41
Forks
12
Language
TypeScript
License
—
Category
Last pushed
Jul 25, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/Heratiki/locallama-mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jonigl/ollama-mcp-bridge
Extend the Ollama API with dynamic AI tool integration from multiple MCP (Model Context...
CodeLogicIncEngineering/codelogic-mcp-server
An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.
sib-swiss/sparql-llm
🦜✨ Chat system, MCP server, and reusable components to improve LLMs capabilities when generating...
thedaviddias/mcp-llms-txt-explorer
MCP to explore websites with llms.txt files
FlowLLM-AI/flowllm
FlowLLM: Simplifying LLM-based HTTP/MCP Service Development