Taming AI Sprawl: Your First Look at the Envoy AI Gateway
summary
Envoy AI Gateway is an open-source CNCF control plane built on Kubernetes Gateway API and Envoy proxy that centralizes API keys, routing and telemetry; a working demo shows multi-model, multi-cloud routing to 15+ providers and self‑hosted models, an external processor sidecar that extracts model and header info, and rate‑limit checks backed by a datastore to enforce token‑based rate limiting. Observability includes per‑request token counts and time to first token, and deployed demos succeed with failover and routing policies.
AI-written summary · about
chapters (7)
- 0:00Introduction and agenda
- 1:11Challenges of AI sprawl
- 3:12Overview of Envoy AI gateway
- 5:20Architecture and components
- 7:37Technical deep dive
- 11:38Live demonstration
- 12:42Key takeaways and conclusion
related talks
17mSeamless AI-as-a-Service across Kubernetes Clusters With Envoy AI Gate...
37mEvolution of Envoy AI Gateway
31mWhen LLMs Hit Production: Why You Need an AI Gateway
04mEnvoy Today: What’s New In Managing Cloud-Native And AI Workl...
17mThe Future of AI Traffic: What's New in Envoy AI Tra...
26mAI Traffic Is Different: Rethinking Proxy Arc...
05mKeynote: Envoy, the Engine for a Cloud Native Security Kernel
26mSecuring the Gateway: A Deep Dive Into Envoy Gateway's Advanced Security Pol...
