peva3/SmarterRouter
SmarterRouter: An intelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI. Features semantic caching, model profiling, and automatic failover for local AI labs.
SmarterRouter acts as an intelligent coordinator for your local AI models and even cloud-based LLMs. It takes your text prompts and automatically sends them to the most suitable AI model you have available, based on its understanding of the task and the models' performance. This is for anyone who uses multiple large language models and wants to ensure the right one is used for the right job, without manual selection or high cloud costs.
Use this if you manage several local AI models (like with Ollama) and want an automated system to pick the best model for each query, optimizing for speed or quality.
Not ideal if you only use a single AI model or primarily rely on a single cloud LLM provider and don't need intelligent routing or local model management.
Stars
63
Forks
3
Language
Python
License
MIT
Category
Last pushed
Mar 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/peva3/SmarterRouter"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neuraxes/neurouter
A powerful router that provides a unified interface for all upstream LLMs
unifyroute/unifyroute
Stop being locked into one LLM provider. UnifyRoute is a self-hosted gateway that routes, fails...
CarloLepelaars/irouter
Access 100s of LLMs with minimal lines of code
deeflect/smart-spawn
Intelligent model routing for AI agents. Auto-selects the right LLM per task based on...
r9s-ai/open-next-router
A lightweight, DSL-driven LLM gateway for routing, patching provider quirks, and normalizing...