AI relay quality monitoring · model verification · Token cost optimization — RelayRadar
This repository also configures its own agents. See what relay-radar tells them →
Skill Claude Code
A testing tool for measuring an AI relay service's connectivity, response delay, throughput, and error rate. It supports Anthropic's API and the OpenAI-compatible API format.
Skill Claude Code
A tool for evaluating and ranking AI relay services. It combines connection speed tests, model-identity checks, and billing reviews into comparison reports.
Skill Claude Code
A guide for reducing Claude Code token costs, where tokens are the units used to process text and code. It examines current usage patterns and suggests ways to spend fewer tokens.
Skill Claude Code
A tool for checking whether an AI relay service is really using the model it claims to provide. An AI relay service passes requests between an application and a model provider.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: