Skip to content
SPECIFICTION
Get listed

Envoy AI Gateway

aigateway.envoyproxy.io

Free plan macOSLinuxAPISelf-hosted
Visit aigateway.envoyproxy.io
Spec score 8.4 #8 of 34 in LLM Gateway Software

What it is

Envoy AI Gateway, now named Agent Router, is an open-source control plane for managing AI and agent traffic through Envoy. It provides an OpenAI-compatible API for hosted and self-hosted models and MCP servers, with integrations for providers including OpenAI, Azure OpenAI, Google Gemini, AWS Bedrock, Mistral, and Anthropic. Traffic controls include model virtualization, provider failover, token quotas, and usage-based rate limiting. Its MCP gateway supports server multiplexing, tool routing, OAuth authentication, and observability; InferencePool support adds routing and load balancing for inference endpoints. Credentials can be managed centrally, and supported short-lived credential flows include AWS Bedrock, Azure OpenAI, and GCP Vertex AI. The project describes metrics collection and monitoring for AI workloads. The free open-source project is listed at free. Its CLI supports local use on Linux and macOS; production Kubernetes deployment uses Envoy Gateway and requires compatible dependencies. The project uses the Apache 2.0 license and points users to Discord and GitHub issues for help.

Spec sheet

Purpose
The open-source project routes and manages generative AI traffic between applications and AI services, with rate limiting and policy control.Read 9 Oct 2026 · theagentrouter.ai
Intended users
The documentation identifies teams sharing models or tools, seeking centralized credentials, quotas, usage attribution, or failover as likely users.Read 9 Oct 2026 · theagentrouter.ai
Deployment
The CLI can run locally on Linux and macOS, and production deployment uses Kubernetes with Envoy Gateway.Read 9 Oct 2026 · theagentrouter.ai
Security
The project describes upstream authentication for securing connections to AI services and says provider credentials can be kept out of application workloads.Read 9 Oct 2026 · theagentrouter.ai
Support
The project directs users to its community Discord and GitHub issues for help.Read 9 Oct 2026 · theagentrouter.ai
License
The project uses the Apache 2.0 license.Read 9 Oct 2026 · theagentrouter.ai
Founded
2024Read 28 Sep 2026 · aigateway.envoyproxy.io
Credential security
Upstream credentials can be centrally managed; supported providers include short-lived credential flows for AWS Bedrock, Azure OpenAI, and GCP Vertex AI.Read 9 Oct 2026 · theagentrouter.ai
Deployment options
The project can run locally as a standalone proxy or deploy to Kubernetes; the site also links to hosted services offered by other providers.Read 9 Oct 2026 · theagentrouter.ai
Inference routing
InferencePool support provides intelligent routing and load balancing for inference endpoints.Read 9 Oct 2026 · theagentrouter.ai
Kubernetes compatibility
The compatibility matrix lists Agent Router v1.2.x with Kubernetes v1.32 or later, Envoy Gateway v1.9.2 or later, and Gateway API v1.6.1.Read 9 Oct 2026 · theagentrouter.ai
Local platform support
The `aigw run` CLI currently supports Linux and macOS.Read 9 Oct 2026 · theagentrouter.ai
MCP gateway
The MCP gateway aggregates tools from multiple servers and supports tool routing, security policies, and observability.Read 9 Oct 2026 · theagentrouter.ai
Observability
The CLI supports OpenTelemetry tracing and can record request and response details; the documentation describes configuration to hide input and output content.Read 9 Oct 2026 · theagentrouter.ai
Provider integrations
The site lists integrations including Anthropic, AWS Bedrock, Azure OpenAI, Cohere, DeepInfra, DeepSeek, Google Gemini, Grok, Groq, Mistral, OpenAI, Together AI, and Vertex AI.Read 9 Oct 2026 · theagentrouter.ai
Renamed project
Envoy AI Gateway is now Agent Router, an Agentic AI Foundation project; the site says the code, maintainers, and APIs remain the same.Read 9 Oct 2026 · theagentrouter.ai
Traffic controls
Capabilities include model virtualization, provider failover, token quotas, and usage-based rate limiting.Read 9 Oct 2026 · theagentrouter.ai
Unified API
It provides an OpenAI-compatible API for routing requests across model providers and lets applications switch models by changing the model name.Read 9 Oct 2026 · theagentrouter.ai

Plans and prices

Open-source project Free Self-managed; local CLI supports Linux and macOS · Kubernetes deployments require compatible dependencies Read 9 Oct 2026 · theagentrouter.ai

Every Envoy AI Gateway plan and price →

Strong points and limits

Strong points

  • OpenAI-compatible API for models and MCP servers.
  • Provider failover and usage-based rate limiting.
  • Centralized credential management.
  • Open-source project listed at free.
  • Self-hosted deployment is supported.

Limits

  • Local CLI currently supports Linux and macOS.
  • Kubernetes deployment requires compatible dependencies.
  • Production deployment uses Kubernetes with Envoy Gateway.

Who it suits

It suits teams sharing models or tools that need centralized credentials, quotas, usage attribution, or failover. It also fits teams prepared to operate a local proxy or a compatible Kubernetes deployment.

Verdict

Agent Router offers a free, self-managed route to centralized AI and agent traffic controls. Teams should account for its Linux and macOS CLI support and Kubernetes compatibility requirements when choosing a deployment.

Where Specifiction places it

Alternatives to Envoy AI GatewayAll alternatives →