anjieyang/IYKYK
IYKYK
This tool helps you manage costs when using large language models (LLMs) by routing your requests to the most appropriate model based on complexity. You feed it your prompts through your existing AI client (like OpenAI SDK or Claude Code), and it decides if a simpler, cheaper model can handle it or if a powerful, more expensive one is needed. This is ideal for anyone who regularly interacts with LLMs and wants to optimize spending without sacrificing performance for complex tasks.
Use this if you want to automatically reduce your spending on large language models by intelligently routing prompts to cheaper models when possible, while ensuring complex queries still go to the best available model.
Not ideal if you only use open-source or local-only models with no associated cost, or if every single one of your prompts genuinely requires the highest-tier, most expensive model.
Stars
20
Forks
2
Language
Python
License
—
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/anjieyang/IYKYK"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
shareAI-lab/learn-claude-code
Bash is all you need - A nano Claude Code–like agent, built from 0 to 1
zebbern/claude-code-guide
Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner...
nicksp/dotfiles
My personal dotfiles: Zsh, Git, VSCode, Cursor, Obsidian, Ghostty, etc.
kalil0321/reverse-api-engineer
Claude engineer that captures traffic, writes documentation and automatically generates API...
CloudAI-X/claude-workflow-v2
Universal Claude Code workflow plugin with agents, skills, hooks, and commands