8 posts tagged with "Features"
Articles about Agent Router features
View All Tags
A token budget for every agent: Agent Router with Agent Substrate
Agent Substrate gives every agent a verified identity, and Agent Router counts the tokens each model call spends. Together they give every agent its own token budget from one rate limit rule, with no custom services. Here is how it fits together, what we tested, and what to watch for.
Nov 6, 2026 · 11 min read
Keep LiteLLM's API, put Envoy behind it: introducing the Agent Router Python SDK
The Agent Router Python SDK keeps LiteLLM's API and sends every call through Agent Router, the open-source AI gateway built on Envoy. Fallbacks, retries, request limits and provider keys move out of your Python process and into the gateway. Moving over is usually one changed import.
Nov 6, 2026 · 8 min read
Multi-User MCP in Production: Per-User Identity at the Gateway Layer
How Envoy AI Gateway's header forwarding gives MCP tool calls per-user identity without OAuth infrastructure — and when you need OAuth instead.
Jul 5, 2026 · 10 min read
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.
Feb 23, 2026 · 8 min read
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.
Dec 8, 2025 · 9 min read
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.
Oct 2, 2025 · 8 min read
Enhancing AI Gateway Observability - OpenTelemetry Tracing Arrives in Envoy AI Gateway
Envoy AI Gateway v0.3 introduces OpenTelemetry tracing with OpenInference conventions, providing complete visibility into LLM application behavior beyond metrics.Understand not just what happened, but why.
Aug 25, 2025 · 6 min read
Envoy AI Gateway Introduces Endpoint Picker Support
Envoy AI Gateway introduces Endpoint Picker Provider support for intelligent inference routing based on real-time AI metrics like KV-cache usage and queue depth—moving beyond traditional load balancing to optimize AI workload performance.
Jul 30, 2025 · 7 min read