Harness 打造小型裝置，掌握 AI 編碼智能體狀態

If you're using Claude Code, Codex, or other AI coding agents, you've probably ended up with a bunch of terminal windows open.

One agent is writing code, another is fixing bugs, and another is waiting for you to answer a question.

Keeping track of everything gets messy pretty quickly.

That's why we've been building Harness at Autonomous.

Harness Workspace

Harness is a workspace where you can run and manage multiple AI coding agents in one place.

Instead of jumping between terminals, you can:

• Run multiple coding agents at the same time.
• See what each agent is working on.
• Know when an agent finishes or needs your input.
• Pick up the conversation from your phone when you're away.

It works with tools like Claude Code and Codex, so you can keep using the agents you're already familiar with.

Harness Device

We also built a small physical device for your desk.

It has a round screen, a microphone, and a speaker.

The idea is simple: you shouldn't have to keep checking your computer just to know what your agents are doing.

The device lets you see their status, get notified when something needs your attention, and interact with them using your voice.

Why we built both

We wanted to make working with AI agents feel a little more natural.

The workspace gives you a place to manage everything. The device keeps your agents within reach, even when you're not staring at your screen.

And when you're away from your desk, you can still check in using the mobile app.

We're still building and improving both.

I'm curious how everyone else handles this. Are you managing your coding agents through separate terminals, tmux, or something else?

Check out Harness App