Open-source LLM router & AI cost optimizer. Routes simple prompts to cheap/local models, complex ones to premium — automatically. Drop-in OpenAI-compatible proxy for Claude Code, Codex, Cursor, OpenClaw. Saves 40-70% on AI API costs. Self-hosted, no middleman.

Lightweight Modular AI Routing Engine for Local LLMs — Run specialised experts efficiently on consumer GPUs using smart Mixture-of-Experts routing.

Local AI load balancer for Ollama fleets — auto-discovery, smart routing, OpenAI-compatible API, zero config. Perfect for Mac Minis & Studios.

Local-first AI model router for serious agents. One endpoint for OpenClaw, Codex, Claude Code, Cursor, Ollama, NVIDIA NIM, and authorized provider fallback.

Benchmark toolkit that measures both cost AND quality for LLM routers

Open-source AI Smart Router. If rules can handle it, don't call AI. 3-layer routing + progressive solidification engine + 100+ models.

AI-powered request routing system built with FastAPI that intelligently directs user queries to appropriate services using rule-based logic and fallback mechanisms, with a responsive web UI.

🖥️ Build and run macOS VMs tailored for OpenClaw development, offering ease for users and power for developers.

Smart AI router — auto-selects best model across Groq, Gemini, OpenRouter & Ollama. 17 models, benchmark mode, task classification, private local inference.

Optimize AI API costs by switching models, measuring efficiency, and avoiding unexpected bills while maintaining performance.

Auto-route tasks to best AI agent