What you can build with it today

• Claude orchestrates, Codex implements. Spawn a Claude lead that hands work to Codex workers, reads their progress live, and steers mid-task when one goes off the rails.
• Adversarial review loops. Run an implementer alongside one or two critics. They iterate until the critic ratifies — no human in the loop.
• Walk-away autonomy. Kick off a multi-step job, close the laptop. Agents keep talking, finishing, and verifying each other's work.

Get started

1. Install the agent-relay CLI:

   curl -fsSL https://raw.githubusercontent.com/AgentWorkforce/relay/main/install.sh | bash

2. Install the orchestration skill:

   npx skills add https://github.com/agentworkforce/skills --skill orchestrating-agent-relay

3. Tell your agent to use it:

   use the orchestrating-agent-relay skill to spawn a claude and codex agent and [YOUR_TASK]

Why not subagents?

Subagents are the right tool when work is a single well-scoped one-shot. Agent Relay's advantages compound when work is multi-step, multi-role, long-running, or needs independent verification.

• Mix models and harnesses. Codex implements, Claude reviews, Gemini verifies — each model used for what it's best at, not whatever the parent harness happens to be.
• Live steering. The orchestrator reads logs and DMs as workers run and can redirect mid-turn instead of waiting for a final report.
• Review as a conversation. The reviewer and implementer talk while the code is being written, not after the fact.
• Swarm patterns out of the box. Review/fix loops, adversarial debate pairs, fan-out → pipeline → gather, lead + workers.
• Audit trail outside the agent. Every DM and channel message shows up in the Agent Relay Observer — full visibility without trusting the parent agent's self-report.

SDK

Spawn and control agents programmatically.

TypeScript / Node.js

npm install @agent-relay/sdk
# or
bun add @agent-relay/sdk

Python

pip install agent-relay-sdk

See the Python SDK for Python usage and adapters.

Quick example

import { AgentRelay, Models } from '@agent-relay/sdk';

const relay = new AgentRelay();

relay.onMessageReceived = (msg) => {
  console.log(`[${msg.from} → ${msg.to}]: ${msg.text}`);
};

const channels = ['tic-tac-toe'];

const x = await relay.claude.spawn({
  name: 'PlayerX',
  model: Models.Claude.SONNET,
  channels,
  task: 'Play tic-tac-toe as X against PlayerO. You go first.',
});

const o = await relay.codex.spawn({
  name: 'PlayerO',
  model: Models.Codex.GPT_5_3_CODEX_SPARK,
  channels,
  task: 'Play tic-tac-toe as O against PlayerX.',
});

await Promise.all([relay.waitForAgentReady('PlayerX'), relay.waitForAgentReady('PlayerO')]);

relay.system().sendMessage({ to: 'PlayerX', text: 'Start.' });

await AgentRelay.waitForAny([x, o], 5 * 60 * 1000);
await relay.shutdown();

More:

• Introduction
• TypeScript SDK README
• Python SDK README

Supported agents and runtimes

First-class support for terminal-native agents:

• Claude Code
• Codex CLI
• Gemini CLI
• OpenCode

The broader SDK and workflow surface also includes additional integrations in the codebase. See the package docs for details.

Development

npm install
npm run build
npm test

References:

• CHANGELOG.md
• GitHub Issues

License

Apache-2.0 — Copyright 2026 Agent Workforce Incorporated

Links: Website · Documentation · Docs (Markdown) · Discord