How-to Guides

Self-hosting Lakera Guard

Self-hosting Lakera Guard allows organizations to keep all data within their own infrastructure. Lakera Guard can be deployed on-premises or in a private cloud, giving you full control over data residency and network access.

Deployment Options

Lakera Guard is available as a fully managed SaaS solution or as a self-hosted deployment. For self-hosted customers, we support flexible deployment models to fit your infrastructure:

Deployment MethodDescription
Kubernetes (Helm)Deploy to any Kubernetes cluster using our official Helm chart from Docker Hub. Includes support for autoscaling, TLS, health probes, and GPU acceleration.
DockerRun the Guard container directly with Docker or any OCI-compatible runtime for simpler setups.
Air-gappedFull offline deployment support for the most restrictive environments. Containers can be exported and loaded without internet access.

What’s Included

The self-hosted deployment includes the following components:

  • Lakera Guard - 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 Guard

Key Capabilities

  • GPU Support - Leverage NVIDIA GPUs for low-latency inference. Compatible with widely available inference GPUs such as the A10G, L4, and A10 — no specialized or cutting-edge hardware required
  • Horizontal Scaling - Stateless containers that scale horizontally
  • Policy Management - Configure guardrails via policy files
  • Audio Defense - Screen audio inputs for audio-based attacks
  • TLS/SSL - Encrypted communication between components
  • Container Versioning - Stable, nightly, and version-pinned releases

Getting Started

To deploy Lakera Guard in your environment, you will need:

Comprehensive deployment documentation — including resource requirements, sizing, latency benchmarks, step-by-step Helm chart installation, GPU configuration, autoscaling, security hardening, Audio Guard setup, and troubleshooting — is available at self-hosted.docs.lakera.ai.

Access to the self-hosted documentation portal is provided to Lakera Guard customers. If you are an existing customer, please contact support@lakera.ai for access. If you are interested in self-hosting Lakera Guard, please contact us.