rig

Integrates with 20+ LLM providers through a single, consistent API, reducing code complexity when switching or combining models, as evidenced by the broad provider support listed.

Offers a unified interface for 10+ vector databases like Qdrant and LanceDB, enabling flexible retrieval-augmented generation (RAG) systems without vendor lock-in.

Enables multi-turn streaming, prompting, and tool-calling for building intelligent agents with minimal boilerplate, as highlighted in the features for scalable LLM applications.

Fully compatible with OpenTelemetry's GenAI Semantic Conventions, facilitating production monitoring and debugging of AI workflows out of the box.