vernLLM
A framework that brings resilience, observability, and control for multiple LLM calls into the application process
SITE CAPTUREBased on information published on the service's website. Selection and review policy
WHAT IT DOES
What does it do?
It connects OpenAI-compatible services, Anthropic, Gemini, and Bedrock through one interface. Retry budgets, circuit breaking, multi-provider fallbacks, rate limiting, caching, and middleware run inside the application process. Providers accessible over HTTP can be connected through the fromFetch adapter.
KEY FEATURES
Key features
- One calling interface for multiple LLM providers
- Retry budgets and circuit breaking
- Multi-provider fallbacks
- Call rate limiting and caching
- Built-in middleware
- Connects HTTP providers through the fromFetch adapter