OmniEdge RouteIQ — Local-First Intelligent Router

OmniEdge RouteIQ is a general-purpose AI agent built for AMD ACT II Track 1. It processes eight benchmark categories: factual knowledge, mathematical reasoning, sentiment classification, summarization, named entity recognition, code debugging, logical reasoning, and code generation. The scoring agent runs inside a public Linux AMD64 Docker container. At runtime, it reads tasks from /input/tasks.json, uses only the models supplied through ALLOWED_MODELS, routes all requests through the evaluator-provided FIREWORKS_BASE_URL, and writes structured answers to /output/results.json while preserving each task_id. RouteIQ follows a Gemma-first model policy. When an approved Gemma 4 model is available, it is selected before permitted fallback models. The implementation avoids hardcoded credentials and model assumptions, supports evaluator-controlled API access, and writes progressive results so completed work survives interruptions. The wider project also includes a FastAPI routing backend and a Next.js command dashboard for demonstrating route decisions, provider status, simulations, metrics, and audit visibility. The benchmark container remains self-contained so automated judging can pull and run it independently.