Aigregator Logo
Aigregator
Agentgateway logo

Agentgateway

Open-source AI-native proxy for securing and routing agent, MCP, and LLM traffic.

Last updated: Jul 26, 2026

About Agentgateway

Agentgateway is an open-source gateway built specifically for AI-native infrastructure. Written in Rust, it acts as a single data plane that routes and secures traffic between applications, large language model providers, Model Context Protocol (MCP) tool servers, and agent-to-agent (A2A) communication, rather than requiring separate tools for each type of traffic. It supports standard HTTP and gRPC routing alongside newer agentic protocols, so teams can manage microservice APIs and agent workloads through the same proxy layer. The tool is aimed at platform engineers and AI infrastructure teams building agentic systems that need governance, visibility, and interoperability across many agents, tools, and models. It includes an LLM gateway with an OpenAI-compatible API that routes across providers such as OpenAI, Anthropic, Google Gemini, and AWS Bedrock, plus an MCP gateway for tool discovery, access control, and audit trails. Observability is handled through OpenTelemetry integration, and it supports policy evaluation and PII redaction for governance needs. Agentgateway originated at Solo.io and has since been donated to the Linux Foundation's Agentic AI Foundation, giving it a vendor-neutral open-source home. It ships as a standalone binary, Docker container, or Kubernetes deployment via Helm. As a young, infrastructure-layer project, it assumes teams already run agentic workloads at some scale and are comfortable with proxy and gateway configuration rather than a plug-and-play consumer setup.

At a glance

Company
Solo.io
Platforms
API
API
Available
Integrations
OpenAI, Anthropic, Google Gemini, AWS Bedrock, Azure OpenAI, Mistral, Kubernetes, OpenTelemetry
Last verified
July 2026
Last updated: July 26, 2026

Who It's For

  • •AI developers and researchers building multi-agent systems.
  • •Platform engineers integrating tools and agents.
  • •Organizations needing secure, observable agent communication.
  • •Tool providers exposing APIs for agent interaction.
  • •Open source and enterprise AI practitioners.

How It Works

  1. 1Connects agents and tools using industry-standard AI protocols like A2A and MCP.
  2. 2Provides a unified, secure, and observable communication layer for agents and tools.
  3. 3Automatically exposes REST APIs as MCP-native tools for easier integration.
  4. 4Includes a self-service developer portal for creating, configuring, and debugging components.
  5. 5Supports agent governance, security, and observability through transparent security policies.

How to Use Agentgateway

  1. 1Access the developer portal to create and configure agents and tools.
  2. 2Connect your agents and tools to the MCP endpoint provided by Agentgateway.
  3. 3Use the platform features to debug, discover, and manage tool and agent interactions.
  4. 4Leverage the supported APIs and protocols for seamless integration.
  5. 5Apply security and governance policies to control communication and data flow.

Key Features

  • •LLM gateway with unified OpenAI-compatible API
  • •MCP gateway with tool discovery, RBAC, and audit trails
  • •Agent-to-agent (A2A) protocol support
  • •Inference routing across GPU pools
  • •OpenTelemetry-based observability
  • •OPA policy evaluation and PII redaction

Use Cases

  • •Routing and securing traffic between agents, LLMs, and MCP tool servers
  • •Managing multi-provider LLM access with budget and failover controls
  • •Adding governance and audit trails to agentic tool usage
  • •Consolidating service, LLM, and agent traffic behind one gateway

Pros & Cons

Advantages

  • •Open source, promotes transparency and community collaboration.
  • •Supports industry-standard protocols for broad compatibility.
  • •Provides an integrated platform for agent management and debugging.
  • •Supports API translation to reduce custom integrations.

Disadvantages

  • •May require technical expertise to set up and customize.
  • •Dependence on industry-standard protocols which might evolve.
  • •Limited user interface features beyond developer tools.

Alternatives

  • Kong
  • Envoy
  • Apigee

Reviews for Agentgateway

0.0

Based on 0 reviews

Rating Distribution

No Reviews Yet

Be the first to share your experience with Agentgateway!

Frequently Asked Questions

What is Agentgateway?

Agentgateway is an open-source gateway built specifically for AI-native infrastructure. Written in Rust, it acts as a single data plane that routes and secures traffic between applications, large language model providers, Model Context Protocol (MCP) tool servers, and agent-to-agent (A2A) communication, rather than requiring separate tools for each type of traffic.

How much does Agentgateway cost?

Agentgateway is free to use.

Is Agentgateway free?

Yes, Agentgateway offers a free plan you can start with.

What are the best Agentgateway alternatives?

Popular Agentgateway alternatives include Kong, Envoy, Apigee.

What is Agentgateway used for?

Agentgateway is commonly used for Routing and securing traffic between agents, LLMs, and MCP tool servers, Managing multi-provider LLM access with budget and failover controls, Adding governance and audit trails to agentic tool usage.

Does Agentgateway have an API?

Yes, Agentgateway offers an API for developers.

What platforms does Agentgateway support?

Agentgateway is available on API.

Information Accuracy

Please note: While we regularly update all tool information including descriptions, features, pricing, and other details, this information may change over time as tools evolve and update their offerings. For the most current and accurate information, we recommend visiting the official website directly. Our goal is to provide you with comprehensive and up-to-date information to help you make informed decisions.