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.
Performs automatic model profiling and benchmarking on local hardware to build decision models for intelligent routing, then continuously learns from user interactions to refine selections. Supports hot-swapping models without restarts, multi-GPU VRAM awareness across NVIDIA/AMD/Intel/Apple Silicon, and can seamlessly blend local Ollama/llama.cpp models with external cloud providers (OpenAI, Anthropic, etc.) under unified intelligent routing.
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
unifyroute/unifyroute
Stop being locked into one LLM provider. UnifyRoute is a self-hosted gateway that routes, fails...
deeflect/smart-spawn
Intelligent model routing for AI agents. Auto-selects the right LLM per task based on...
neuraxes/neurouter
A powerful router that provides a unified interface for all upstream LLMs
r9s-ai/open-next-router
A lightweight, DSL-driven LLM gateway for routing, patching provider quirks, and normalizing...
CarloLepelaars/irouter
Access 100s of LLMs with minimal lines of code