A framework for developing LLM (Large Language Model) applications with multiple conversational agents.

These agents can collaborate to solve tasks and can interact seamlessly with humans.

It simplifies complex LLM workflows, enhancing automation and optimization.

It offers a range of working systems across various domains and complexities.

It improves LLM inference with easy performance tuning and utility features like API unification and caching.

It supports advanced usage patterns, including error handling, multi-config inference, and context programming.