Baseline+ AddPrompt Injection ProtectionGuardrails for untrusted retrieved text, tool output, and user-supplied instructions.Stable · v1.0.0 · MIT
Guide+ AddLLM Observability and EvaluationTracing, metrics, and lightweight eval harnesses for LLM features in production.Stable · v1.0.0 · MIT
Guide+ AddOpenAI IntegrationProduction-minded OpenAI API integration with auth, retries, and observability hooks.Stable · v1.0.0 · MIT