The Model Registry Maintainer skill provides a standardized workflow for keeping local AI model registries up-to-date with the rapidly evolving landscape of LLM providers. It guides developers through updating backend capabilities and token management files, ensuring that applications have accurate data regarding model release dates, pricing structures, and context window limits. By leveraging external databases like LiteLLM and OpenRouter, this skill streamlines the process of adding new models from providers like OpenAI, Anthropic, and Google while maintaining data integrity through built-in validation and documentation scripts.
주요 기능
01Standardized workflows for adding new frontier models and providers
02Pricing and token limit synchronization for over 500 AI models
03Comprehensive registry management for model features and backend capabilities
0481 GitHub stars
05Built-in validation commands for testing registry updates
06Automated data sourcing from LiteLLM and OpenRouter APIs
사용 사례
01Adjusting token cost estimation logic after a provider announces pricing reductions
02Adding custom or internal organizational models to a backend capabilities framework
03Updating project registries immediately following a new model release from a major AI provider