OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Infrastructure

Agentgateway

Agentgateway is an open-source proxy for communication between AI agents, tools and language-model providers. Built around MCP and A2A, it provides routing alongside security, observability and governance features.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Agentgateway — OpenViST project profile in Agent Infrastructure.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when agent, tool and model connections need a shared proxy layer, or when routing and operational controls should sit at the infrastructure layer. Choose the standalone documentation for flat YAML configuration or the Kubernetes path for its built-in controller and Gateway API support.

Who it is for

  • Teams connecting agents to multiple language-model providers.
  • Teams exposing tools or external data sources to models through MCP.
  • Platform engineers connecting agents to tools or other agents and managing traffic centrally.

Documented uses

  • Route model requests to providers through a unified OpenAI-compatible API.
  • Connect models with MCP tools and external data sources, including through tool federation.
  • Enable agent-to-agent communication with capability discovery and task collaboration.
  • Apply authentication, authorization, rate limiting, guardrails and telemetry to agent traffic.
  • Route to self-hosted models using Kubernetes Inference Gateway extensions and model-serving signals.
Before you choose

Requirements & limits

The project is open source under the Apache-2.0 license. Deployment documentation covers standalone configuration and Kubernetes.

  • The two documented deployment paths are standalone flat-YAML configuration and Kubernetes with a built-in controller and Gateway API support.
  • Model-provider routing uses a unified OpenAI-compatible API; listed providers include OpenAI, Anthropic, Gemini and Amazon Bedrock.
  • MCP support lists stdio, HTTP, SSE and Streamable HTTP transports, plus OpenAPI integration and OAuth authentication.
  • Authentication and policy options include JWT, API keys, OAuth and CEL-based RBAC; telemetry uses OpenTelemetry.
  • Self-hosted inference routing is described in connection with Kubernetes Inference Gateway extensions.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Choose an agentgateway deployment path

Select the documented standalone or Kubernetes deployment documentation for your environment.

Before you start

  • Choose between running agentgateway as a standalone binary or in Docker, and deploying it on Kubernetes.

Steps

  1. For a standalone binary deployment, open the standalone documentation.

  2. For Kubernetes deployment, open the Kubernetes documentation and use its built-in controller and Gateway API guidance.

Expected outcome

You reach the documentation for the chosen deployment type: standalone binary or Kubernetes.

Guide limitations

  • This guide selects a documentation path; it does not provide installation, configuration, or deployment steps.
Documentation 1 ↗Documentation 2 ↗Documentation 3 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
agentgateway/agentgateway · Official homepage title · retained in its source language
How we review sourcesSuggest a correction