ultra-lightweight, mathematically robust prompt compression middleware

An intelligent, low-latency local LLM router that reduces AI costs by 30-70%. Uses a self-hosted classifier to automatically route prompts to the most cost-effective model without external API overhead.

Local hooks that catch vague AI-agent prompts before they burn tokens.

System-level lint for multi-agent harnesses. Catches the 21 structural traps single-file linters miss — including the LLM-when-you-should-use-code patterns that burn tokens.

AI-powered AWS cost analysis and optimization agent using natural language — built with Amazon Bedrock AgentCore and Strands Agents SDK

# AWS Bedrock Claude REST API with Terraform This project provides a complete Terraform setup to expose Claude AI models through AWS Bedrock via a REST API. All usage is billed directly through AWS, eliminating the need for separate Anthropic API credits.

Energy-efficient AI prompt routing system — sends simple prompts to lightweight models and reserves larger models for complex reasoning to cut compute, latency, and energy.

Optimize AI model costs and automatically switch between models for better performance.

AIMUX (AI Multiplexer) — terminal-native multi-model AI orchestrator for developer workflows. Classifies tasks, routes to the cheapest viable model, launches the right CLI, tracks cost, and fails over across providers.