Portkey AI Gateway

Superagent protects AI applications against prompt injections, data leaks, and harmful outputs, embedding safety directly into your app.

NVIDIA NeMo Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational systems, supporting topic control, safety enforcement, and dialog guidance.

CVS Health's open-source uncertainty quantification library for language models, providing UQ-based hallucination detection with confidence scoring and mitigation tools to identify and reduce unreliable LLM outputs.

Guardrails AI adds programmable guardrails to large language models, ensuring reliability and safety through input/output validation, structured data extraction, and custom validators.