Agent Relay is a low-latency messaging and coordination layer for AI agents.

Think: agents that actually talk to each other. In real time. Without rewiring your setup.

Agent Relay is a developer-first protocol and runtime that lets AI agents communicate like a team instead of a bunch of isolated scripts.

If your agent can print to stdout, it can participate.

Right now, most agents:

• Run alone
• Can’t coordinate
• Only "communicate" after they’re done

That’s not how teams work. And agents are teams.

Agent Relay gives them a shared, fast, boring-in-the-best-way communication layer.

• ⚡ Sub-5ms message delivery
• 🔌 Works across providers (Claude, Codex, Gemini, custom)
• 🧠 No config changes to your existing agent setup
• 🖥️ CLI-native — pipes, streams, stdout, not frameworks

No YAML marathons. No SDK lock-in. No magic.

You’ll find:

• Core protocol implementations
• CLIs and SDKs
• Demos and examples
• Weird experiments that might become real features

Some repos are stable. Some are spicy. All are moving.

• Primitives over platforms
• Interop over lock-in
• Fast by default
• If it’s not simple, it’s not done

Agent Relay should fade into the background and just work.

Early. Actively built. Opinions welcome.

APIs will change. That’s the fun part.

• Docs: https://docs.agent-relay.com
• Hosted Version: https://agent-relay.com

Built for agents that shouldn’t have to work alone.