Open beta

Your AI agents are working.
You don't have to babysit them.

Watch and steer Claude Code, Codex, Gemini CLI, Grok, Cursor, and local Ollama models from your phone, wherever they run. Approve a tool call, answer a question, or send a new prompt with one tap, end-to-end encrypted, from anywhere.

Download for macOS

On Linux? Install with one command →

Available on iPhone and/or Android

Agents At Work supports

Claude Code Codex Gemini CLI Grok Cursor Ollama

Not affiliated with Anthropic, OpenAI, Google, xAI, Anysphere, or Ollama.

New

Run open-source AI models on your own hardware.
Control them from your phone.

Agents At Work works with Ollama, an open-source runtime for running AI models locally. Pick a model, start a session, and send prompts from your phone exactly as you would with Claude, Codex, or any other agent. Any model works for chat, writing, and Q&A. Models in the qwen2.5 and qwen3 families also unlock Agentic mode, where the model reads and writes files, runs shell commands, and completes multi-step tasks on your computer while you're away from it, the same workflow as Claude Code, but private and free.

The more memory your machine has, the more capable the model, from a 7 B model on 8 GB to models that rival cloud services on 64 GB or more. Which model fits your machine →

Because everything runs on your hardware, your prompts never reach a third-party AI service. No API key. No per-query charges. No subscription beyond Ollama itself, which is free and open source. On a Mac you start an Ollama session from the app's Ollama tab; on Linux, aaw start ~/proj --agent ollama --model qwen2.5.

🔒Fully private, prompts never leave your computer
No API key, no per-query charges, ever
🛠Chat or Agentic mode, detected automatically by model
📱Remote control from iPhone or Android

Not just for developers

"I use it for writing posts and articles, planning our Europe trip, brainstorming, basically anything where I want an AI agent working on something while I'm away from my desk. Had an idea during a run last week, fired off a prompt from my phone, and came back to a full draft."
✍️ Writing & editing 🗺️ Trip planning 💡 Brainstorming 📝 Drafts & outlines 🔍 Research

How it works

Want the full walkthrough? See the tutorial →

terminal: your Mac or Linux box
$claude  # start agent, leave it running
→ Reading codebase…
→ Editing UserService.kt
→ Agent wants to run: npm run build
📱 Push notification sent to your phone
→ Waiting for approval… _
✓ Approved from mobile. Continuing.
→ Build complete.
  1. Install the companion on the computer where your agents run: the menu bar app on a Mac, or the aaw command-line tool on Linux. Sign in, and that computer is ready to bridge to your phone.
  2. Download the mobile app on iPhone (App Store) or Android (Google Play). No sign-in needed on the phone. Open it, go through the quick onboarding, and tap Scan QR Code. Point your camera at the QR shown by the Mac app, or printed in the terminal by aaw login on Linux, done. Your phone is linked, and the communication channel is end-to-end encrypted, in one step.
  3. Leave Claude, Codex, Gemini, Grok, Cursor, or Ollama running. You'll get a notification the moment the agent needs a decision. Tap Yes or No right from the notification, or from your Apple Watch.

Control everything from your pocket

Four agents running in parallel. One tap to approve. Zero desk required.

Agents At Work
MacBook Pro
my-app Running · 12 min
Claude
api-service Waiting for input
Codex
research-bot Running · 3 min
Gemini
data-pipeline Running · 47 min
Claude
mobile-ui Running · 1 min
Gemini
ubuntu-dev
backend-refactor Running · 8 min
Claude
test-suite Running · 2 min
Codex
docs-gen Waiting for input
Gemini
code-gen Running · 5 min
Grok
ui-polish Running · 3 min
Cursor
blog-draft Running · 2 min
qwen2.5
infra-config Stopped
Codex
‹ Back my-app Claude
Claude is working…
Refactor the auth module and add unit tests
Reading auth module… Found 3 files to update. Starting with AuthService.swift
Claude is working
Permission required
Claude wants to run a command
run_command npm run test
✓ Tests passed (14/14). Updating AuthService.swift with refactored implementation…

Everything you need to step away

Push notifications with action buttons

When the agent asks to edit a file, run a command, or make a decision, you get an instant notification with Yes / No buttons. Answer directly from the lock screen, no need to unlock or open the app.

Live conversation feed

Every message, tool call, and assistant response streams to your phone in real time. A status bar shows "Wrote main.py", "Ran: npm test" between turns so you always know what's happening.

Mac and Linux

On a Mac, a menu bar app. On Linux, a background service and the aaw command that run headless: start an agent over SSH on a home server or a cloud VM, log out, and keep controlling it from your phone. Both pair with the same phone app, and every machine shows up in one list.

End-to-end encrypted

Conversation content is AES-256 encrypted on your computer before it reaches Firebase. The encryption key is exchanged via a one-time QR scan, only your computer and phone can read it. Firebase never sees plaintext.

Auto-approve mode

Toggle "Allow all for this session" when you trust the agent to proceed without interruption. Resets automatically when you send a message or the session ends.

Multiple computers and projects

Add as many computers as you like, Mac or Linux. Each shows detected agents, live sessions, and usage stats. Tap any project to open its conversation.

Personal · $5.99/mo, Pro · $12.99/mo  ·  See pricing →

Agents At Work - Monitor and control AI agents from your phone | Product Hunt

Sounds exactly like what I wanted. I know some of the agents already support this, but not all to the same feature set and I bounce around between my agents a lot. Excited to see how this turns out!

— Mike, on Product Hunt

Our phone is the sun of our personal device solar system, having the remote control there makes so much sense!

— Tim, on Product Hunt

Up and running in under a minute

Five quick screens. Tap the phone to walk through them. Want the full walkthrough? See the tutorial →

Onboarding: welcome Onboarding: install Mac app Onboarding: subscription Onboarding: end-to-end encrypted Onboarding: scan QR code

What you need

Mac

  • macOS 13 Ventura or later
  • Claude Code, Codex, Gemini CLI, Grok, or Cursor, or Ollama for private local models
  • Agents At Work companion app

Linux

  • Ubuntu, Debian, Fedora, RHEL, or any systemd distro
  • tmux 3.2 or newer, Python 3.11 or newer
  • Claude Code, Codex, Gemini CLI, Grok, or Cursor, or Ollama for private local models
  • The aaw command-line tool

iPhone

  • iOS 17 or later
  • Available on the App Store
  • Links to your computer via QR scan, no account needed on phone

Android

  • Android 8.0 (API 26) or later
  • Available on Google Play
  • Links to your computer via QR scan, no account needed on phone

Have a proposal, or need to deploy this to a bigger team?

Happy to work with you directly on rollout, custom integrations, or whatever you have in mind. Let's figure it out together.

We'll get back to you within 1–2 business days.

Get the companion for your computer

Free on both platforms. The Mac app is notarized by Apple. The Linux release is signed, and the installer verifies it before touching your machine, no root needed.

macOS

Menu bar app. Direct download, no Mac App Store required.

Download AgentsAtWork.dmg
macOS 13 Ventura or later Apple Silicon (M1 and later) Version 1.4 (build 65) Free
Installation
  1. Open the downloaded .dmg file.
  2. Drag Agents At Work to your Applications folder.
  3. On first launch, macOS may show a Gatekeeper dialog, click Open. The app is notarized by Apple.
  4. Sign in with Google or email/password and follow the in-app walkthrough.

Linux

A background service plus the aaw command. Runs headless on laptops, servers, and cloud VMs.

curl -fsSL https://agentsatwork.app/install-linux.sh | bash
Ubuntu, Debian, Fedora, RHEL tmux 3.2+, Python 3.11+ Version 0.1.0 (build 6) Free
Installation
  1. Run the command above. It installs to ~/.local/share/agentsatwork and starts a user service that keeps sessions bridged after you log out.
  2. Run aaw login. On any device, sign in at agentsatwork.app/link-linux and type the one-time code it shows.
  3. Scan the QR code aaw login prints with the phone app. Your Linux machine appears next to your other computers.
  4. Run aaw start ~/your/project, or just claude in the project folder. Linux walkthrough →