AI SRE tools for RCA, Incident Response, Cost-Saving, Infra management, DevOps and more

ultra-lightweight, mathematically robust prompt compression middleware

Laravel AI Guard 🛡️💰🤖 - Control and optimize AI costs in Laravel AI SDK applications 🚀 Track OpenAI & LLM token usage 📊, estimate AI costs before execution ⚠️, enforce AI budgets 🧾, and prevent unexpected billing spikes in production 💥.

Local, cache-aware LLM usage and cost telemetry for OpenClaw.

Production operations framework for AI-powered SaaS. The architectural patterns, failure modes, and operational playbooks that determine whether your AI systems scale profitably or fail expensively.

Token-efficient web research for AI agents; tinyfish search + Groq summarisation, 99% fewer tokens than raw HTML

OpenAI-compatible LLM gateway that reduces API costs using Redis exact cache and Qdrant semantic cache.

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.

AI Image Generation Cost Analysis

Rust CLI that reduces Claude Code token usage by 60-90%. Transparent proxy for git, find, grep, and dev commands — filters noise before it hits the context window.

Open-source, self-hostable AI cost & workflow observability. Find the prompt, customer, model, and workflow path behind every LLM cost spike — without a proxy.

Cut Claude Code spend without sacrificing quality — and prove it. Haiku/Sonnet/Opus router with real $-saved numbers, not vibes.

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.

LLM cost calculator, token counter, latency benchmark, CI guardrail, MCP server, and VS Code/Cursor extension.

One command to audit what your Claude Code setup loads at runtime. Free.

AI Video Generation Cost Analysis

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