AgentGateway logo

AgentGateway

AgentGateway is an open-source, AI-native proxy and gateway for routing, observing, and governing traffic to and from AI agents, LLM providers, and MCP servers. Built on the A2A and MCP protocols, it provides a unified gateway for LLM consumption, MCP tool federation, agent-to-agent communication, security, and observability. AgentGateway supports multi-provider LLM routing across OpenAI, Anthropic, Google Gemini, AWS Bedrock, and Azure OpenAI with built-in RBAC, JWT authentication, rate limiting, and OpenTelemetry integration.

1 APIs 10 Features
AI GatewayAPI GatewayMCPLLMAgent-to-AgentOpen SourceCNCFObservabilitySecurity

APIs

AgentGateway

AgentGateway provides AI-native gateway capabilities for routing LLM traffic, federating MCP tools, enabling agent-to-agent communication, and applying security and observabilit...

Features

LLM Gateway

Routes traffic to OpenAI, Anthropic, Google Gemini, AWS Bedrock, and Azure OpenAI through a unified API with model aliasing, failover, and load balancing.

MCP Gateway

Connects LLMs to tools via Model Context Protocol with static and dynamic routing, tool federation, and stateful MCP sessions.

Agent-to-Agent (A2A) Gateway

Enables secure, governed communication between AI agents using the A2A protocol for multi-agent orchestration.

Inference Routing

Intelligently routes requests to self-hosted models based on GPU utilization and request priority.

Security and Authentication

Provides JWT, OAuth2, API key management, CORS, CSRF protection, MCP authentication, and external authorization support.

Traffic Management

Supports request routing and matching, header manipulation, rate limiting, retries, gRPC routing, traffic splitting, and direct responses.

Observability

Integrates with OpenTelemetry for metrics, traces, and access logging with a built-in Admin UI and debugging tools.

Guardrails

Applies prompt guards, content filtering, regex filters, moderation policies, and custom webhooks for AI safety.

Cost Controls

Tracks budget and spend limits per user, team, or application with RBAC-based controls on LLM consumption.

Prompt Enrichment

Supports prompt templates and enrichment for standardizing and augmenting requests before routing to LLM providers.

Use Cases

Unified LLM Routing

Route requests across multiple LLM providers with a single API, enabling failover, load balancing, and cost optimization without changing client code.

MCP Tool Federation

Aggregate tools from multiple MCP servers behind a single gateway endpoint, enabling agents to discover and invoke tools from any connected MCP server.

Enterprise AI Governance

Apply organization-wide security policies, rate limits, budget controls, and content filters to all AI agent traffic through a centralized gateway.

REST API to MCP Conversion

Convert existing REST APIs into MCP-native tool endpoints that AI agents can discover and invoke through the Model Context Protocol.

Multi-Agent Orchestration

Enable secure agent-to-agent communication using the A2A protocol, allowing specialized agents to delegate tasks to each other through the gateway.

Observability and Debugging

Collect unified telemetry across all AI agent and LLM interactions to monitor cost, latency, and behavior at scale.

Integrations

OpenAI

Route to OpenAI GPT models through the AgentGateway LLM backend with model aliasing and budget controls.

Anthropic

Connect to Anthropic Claude models via the unified LLM gateway with failover and load balancing.

Google Gemini

Route traffic to Google Gemini models through the AgentGateway multi-provider backend.

AWS Bedrock

Integrate with AWS Bedrock for managed LLM access via the AgentGateway routing layer.

Azure OpenAI

Route requests to Azure-hosted OpenAI models through the unified gateway API.

Ollama

Connect to locally hosted Ollama models for self-hosted inference routing.

vLLM

Route to vLLM inference servers with GPU utilization-aware routing for optimal performance.

OpenTelemetry

Export metrics, traces, and logs to any OpenTelemetry-compatible observability backend.

Kubernetes Gateway API

Deploy and configure AgentGateway on Kubernetes using the standard Gateway API for dynamic configuration.

Semantic Vocabularies

Agentgateway Context

5 classes · 21 properties

JSON-LD

Resources

👥
GitHubOrganization
GitHubOrganization
🔗
LLM Backend Schema
JSONSchema
🔗
MCP Target Schema
JSONSchema
🔗
Route Schema
JSONSchema
🔗
JSONLD
JSONLD
🔗
Vocabulary
Vocabulary
🌐
Portal
Portal
🔗
Documentation
Documentation
🚀
GettingStarted
GettingStarted
💬
Support
Support