LLMKit

Provides a unified interface to Arize Phoenix's capabilities for managing prompts, exploring datasets, and running experiments across different LLM providers

Drop-in proxy between applications and REST/GraphQL/SQL/file endpoints that automatically handles schema drift detection, data transformation, and pipeline healing using LLM-assisted mapping to create cached JSONata transforms that run without latency and regenerate when upstream schemas change.

Exposes monorepo workspace architecture, generators, tasks, and documentation to language models