← All projects
Running AI at scale

Agentgateway

A traffic controller that adds security, monitoring and rules to how AI agents talk to models, tools and each other.

New this week

What it does

Agentgateway is a proxy, a go-between that sits in the middle of AI agents and the things they connect to. It handles agent-to-model, agent-to-tool and agent-to-agent traffic, using the MCP and A2A standards for AI connections.

It can route requests to major AI providers through one interface, with spending limits, load balancing and backups. It can also filter content, control who can do what, limit request rates and record detailed logs.

It can run on its own or inside Kubernetes, a common system for running software on servers, and has a built-in web interface.

Who it's for

Platform and infrastructure teams running AI agents in production.

Can I use it without coding?

Developers only. It is server software set up with configuration files. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Server, Cloud
Computer
Made for servers or data centres
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe