An intelligent LLM inference gateway that dynamically routes user queries to optimal model tiers (Llama-3.1 8B/70B) based on real-time complexity, reasoning depth, and ambiguity analysis.

A lightweight, premium API monitoring dashboard with visual 24h status bars, latency tracking, and automated downtime alerts. Built with Next.js 15, TypeScript, and GitHub Actions.

Android Performance Monitoring SDK for app start time measurement, frame drop detection, ANR monitoring, memory tracking, and network latency analysis.

Real-time API latency monitor for LLM providers - track OpenAI, Anthropic, Google, Azure response times