QwenPaw
MCPApache-2.0
QwenPaw: Your personal AI assistant, deployable locally or in the cloud, with memory, multi-agent support, and multi-cha
34k·AI Agents·Open source
Alternative to
SmarterRouter
Open sourceIntelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI with semantic caching and auto-failover.
150MIT
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.
Pros
- +Zero manual model selection with intelligent routing
- +Local-first, zero cost, works with existing models
- +Production-ready with monitoring, metrics, and error handling
- +Drop-in replacement for OpenAI-compatible clients
Cons
- −Initial profiling takes 30-60 minutes
- −Requires Docker and GPU setup for optimal performance
- −Limited to supported backends (Ollama, llama.cpp, OpenAI)
Target audience: Developers and AI labs running local LLMs who need automated model routing and VRAM management.
Related tools
Other open-source tools that share tags with SmarterRouter.
Horizon
MCPMIT
AI-powered news radar generating daily bilingual briefings in English & Chinese.
9k·Other·Open source
LocalAI
MCPMIT
Open-source AI engine to run LLMs, vision, voice, image, video on any hardware, no GPU required.
49k·Self-Hosted AI·Open source
Alternative to
Codewhale
MCPMIT
Open-source Rust terminal coding agent that works with any model, hosted or local.
41k·AI Agents·Open source
Alternative to
93+ production-ready AI projects with tutorials on LLMs, RAG, and agents.
37k·Developer Tools·Open source
Vane
MIT
Self-hosted AI answering engine with privacy, local LLM support, and cited sources.
37k·Self-Hosted AI·Open source
Alternative to