VernLLM

VernLLM이란?

VernLLM is the reliability layer for OpenAI compatible LLM applications. A dependency light wrapper that adds retries with backoff, timeouts, circuit breakers, caching, structured outputs, schema validation, usage tracking, and observability through one typed interface. Works with OpenAI, Groq, Mistral, DeepSeek, Anthropic, Gemini, AWS Bedrock, and custom endpoints. Battle tested with 110+ tests. Open source, MIT licensed, and built for developers.