Integrations
Where an inline security layer attaches in each framework and model API, taken from that project's own documentation and linked to it. We publish no tested-compatibility claim for any of them: each page says so, and says what to ask for in writing instead.
Amazon Bedrock guardrails and inline security
How Bedrock's ApplyGuardrail API works, where a separate inline layer attaches, and how to decide which controls belong to the platform and which do not.
· 4 min readAmazon BedrockAWSguardrailsintegrationGoogle Vertex AI and inline LLM security
The google-genai SDK documents a base_url option for putting a gateway in front of the API — what that pattern enforces, and what routes around it.
· 4 min readVertex AIGoogle CloudintegrationgatewaySecuring LangChain applications
Where a security layer attaches in a LangChain agent — the documented middleware hooks, what each one can enforce, and what middleware alone cannot cover.
· 5 min readLangChainintegrationmiddlewareagentsSecuring LlamaIndex applications
LlamaIndex instrumentation observes the pipeline rather than intercepting it — where that leaves enforcement in a RAG application, and what to attach instead.
· 4 min readLlamaIndexintegrationRAGobservabilitySupported models and frameworks
The compatibility matrix for SecureAI Guard. It is not filled in yet, so this page is withheld from search results rather than published with plausible guesses.
· 3 min readcompatibilityintegrationssupport matrixThe Anthropic API and inline LLM security
The Anthropic SDKs document a base_url option and an ANTHROPIC_BASE_URL variable — the cleanest attachment point there is, and what still gets past it.
· 4 min readAnthropicClaudeintegrationgateway