Built together. Built in the open.
Envoy AI Gateway is the result of the community coming together to address GenAI traffic handling needs using Envoy.
v0.5 Release now available
The v0.5 Release of Envoy AI Gateway is now available. See the release notes for more information.
Get involved in the community
Join our community on Slack, join the conversation on GitHub, and attend our Monday community meetings. See links in footer.
Latest from the Blog
Stay up to date with the latest news, features, and insights from the Envoy AI Gateway team.
Benchmarking Envoy AI Gateway Control Plane Scaling
How many AIGatewayRoute resources can Envoy AI Gateway handle? We benchmarked the control plane scaling to 2,000 routes and measured latency, CPU, and memory usage.
The Reality and Performance of MCP Traffic Routing with Envoy AI Gateway
In this article explore how Envoy AI Gateway handles stateful MCP sessions, keeps performance competitive, and stays aligned with the broader Envoy ecosystem.
Announcing Model Context Protocol Support in Envoy AI Gateway
Envoy AI Gateway now supports Model Context Protocol (MCP), bringing enterprise-grade security, routing, and observability to AI agent tool integrations with full spec compliance, OAuth authentication, and zero-friction deployment.
Supported LLM Providers
With the latest version of Envoy AI Gateway you can route traffic to these LLM providers, displayed alphabetically, out of the box.
For more information and the most up-to-date provider integrations, check out our provider documentation.
Adopters
See who's using Envoy AI Gateway.
Using Envoy AI Gateway? We'd love to feature your logo!
Add Your Logo