The community around Kubernetes includes a number of Special Interest Groups (SIGs) and Working Groups (WGs) facilitating discussions on important topics between interested contributors. Today, we’re excited to announce the formation of the AI Gateway Working Group, a new initiative focused on developing standards and best practices for networking infrastructure that supports AI workloads in Kubernetes environments.
What is an AI Gateway? In a Kubernetes context, an AI Gateway refers to network gateway infrastructure (including proxy servers, load-balancers, etc.

K8S Contributors

The Kubernetes community has formed the AI Gateway Working Group (WG AI Gateway), a new initiative to develop standards and best practices for networking infrastructure supporting AI workloads. An AI Gateway in Kubernetes context refers to network infrastructure implementing the Gateway API with AI-specific capabilities like token-based rate limiting, fine-grained access controls, payload inspection, and AI-protocol routing. Active proposals include payload processing (covering security features like prompt injection protection and optimization features like semantic routing and caching) and egress gateways (for securely routing traffic to external AI services like OpenAI, Vertex AI, and Bedrock). The group is presenting at KubeCon Europe 2026 in Amsterdam and welcomes contributions from gateway implementers, platform operators, and AI developers via GitHub, weekly meetings, and Slack.

Announcing the AI Gateway Working Group