Self-hosting AI Guardrails
Self-hosting Check Point AI Guardrails allows organizations to keep all data within their own infrastructure. You can deploy AI Guardrails in your own data center or in a private cloud, so you decide where data resides and which networks can reach it.
Deployment options
AI Guardrails is available as a fully managed SaaS solution or as a self-hosted deployment. Self-hosted customers can choose from these deployment methods:
What’s included
The self-hosted deployment includes the following components:
- AI Guardrails: the core security screening service for text-based threat detection
- API Gateway: request routing and prompt chunking for high-throughput workloads
- Triton Inference Server: GPU-accelerated inference for text classifiers
- Triton TensorRT-LLM: GPU-accelerated inference for Audio Defense
Key capabilities
- GPU Support: use NVIDIA GPUs for low-latency inference. Contact us for current hardware recommendations for your deployment
- Horizontal Scaling: stateless containers that scale horizontally
- Policy Management: configure guardrails via policy files
- Audio Defense: screen audio inputs for audio-based attacks
- TLS: encrypted communication between components
- Container Versioning: stable, nightly, and version-pinned releases
Getting started
To deploy AI Guardrails in your environment, you need:
- A valid AI Guardrails Enterprise license
- Container registry credentials (provided by Check Point)
- A Kubernetes cluster or Docker-compatible host
The full deployment documentation is available at self-hosted.docs.lakera.ai. It covers resource requirements, sizing, latency benchmarks, step-by-step Helm chart installation, GPU configuration, autoscaling, security hardening, Audio Defense setup, and troubleshooting.
AI Guardrails customers get access to the self-hosted documentation portal. If you are an existing customer, contact your Check Point representative for access. If you are interested in self-hosting AI Guardrails, please contact us.