Your agent froze, waiting for your yes.

Pushary sends the question to your phone. Tap Approve and it keeps working.

Start your trial

Pushary sends the step that needs you, not your codebase.

$ claude refactor auth/ --apply
rewrote session + token refresh
12 files changed, tests passing
Tap Approve to try it
Works with
Claude CodeCodexAntigravity CLIHermesCursor
Hacker NewsFeatured on Hacker News
6+
agents, one setup
1 tap
to approve or deny
Any device
iPhone, Android, Mac, Windows, Linux
< 2 min
one-command setup

Walk away. Come back to finished work.

Without Pushary

  1. Hand off a long task. Walk away.

  2. The agent reaches a step it should not take alone. It stops and waits.

  3. You come back. It has not moved in 37 minutes.

With Pushary

  1. Hand off the same task. Walk away for real.

  2. Your phone buzzes. Approve the change before it goes live? You tap yes.

  3. You come back. The task finished half an hour ago.

Your agent should not wait 37 minutes for a single yes.

Start your trial

What is Pushary?

Pushary is the control panel for AI agents. When your agent needs a yes, Pushary sends the question to your phone, your Mac, Slack or the web app. You approve or deny, and every answer is saved. Works with Claude Code, Codex, Cursor, Hermes, Windsurf, and any MCP agent.

Your AI agents send permission requests to Pushary, which delivers them to your phone, your Mac's notch, Slack, the web app, and an audit trail.

Your agents

Claude Code
Codex
Cursor
Antigravity CLI
Hermes
Your phone
Your Mac
Slack
Web app
Audit trail

Where it reaches you

+ any MCP agent, wired the same way

How it works

See the whole flow

One approval, start to finish, in 21 seconds.

  1. 01Connect once. Set up Pushary on Mac, Windows or Linux. Connect your agents and pair your iPhone or Android.
  2. 02At your desk. Answer from the notch on Mac. On Windows or Linux, keep approvals in your terminal.
  3. 03Away from your desk. Choose phone delivery and leave your computer running. Answer on iPhone or Android to keep your agent moving.

Stay in control

Set the rules once. Approve only what matters.

YOLO mode approves everything, including the rm and the deploy. Pushary auto-runs only the safe steps and pings you for the ones you cannot undo.

Auto-approve the safe stuff

Low-risk steps you can undo. Allow them once and stop seeing them.

The risky ones come to you

Deleting, deploying, spending money, anything you cannot undo. These go to your phone.

You set the wait time

Set how long each step waits. If you do not answer, your rule decides: deny, or hand it back to the terminal.

Your agent control panel

Every agent in one place. See which one is waiting on you, plus the full audit trail.

One command sets up every agent.

It finds the agents on your computer and connects them all to your phone, in under two minutes.

terminal
npx pushary@latest setup

Works with your agent

Windsurf or another MCP client? Connect it by hand
Works on Mac, Windows and Linux.

On a Mac? The Pushary app can set it up for you, no terminal needed.

  1. 01Run the command on your computer.
  2. 02Open the QR link on your phone. Install the app if needed.
  3. 03Sign in and activate your plan, then approve the connection.
  4. 04Answer the test question, then restart your agent.
Start your trial

$9.99/mo after a 3-day free trial. Cancel anytime.

Already have an account? Get the phone and Mac apps

Questions, answered

Can I approve an AI agent from my phone?
Yes. Setup shows a QR code, you scan it once with your phone camera, and questions start arriving on your lock screen. Works on iOS and Android. App or browser, your choice. From the notification you approve, deny, choose an option, or type a reply, and the agent keeps going.
How much does it cost?
The Agent plan is $9.99 a month after a 3-day free trial, with 5,000 notifications a month, about 160 a day. It covers every agent you run. Agent Pro, at $19.99 a month, adds unlimited notifications, budgets, and up to 5 people.
Is my code sent to Pushary's servers?
Not on routine product paths. The decision path transmits notification metadata (title, body text, tool name). Pushary-launched transcripts are redacted and encrypted on your machine; your phone can decrypt them, and authorized Pushary compliance admins can recover them for documented legal obligations.
How long does it take to set up?
Under 2 minutes. Run npx pushary@latest setup. It finds Claude Code, Codex, Cursor, Hermes and the other agents on your computer and connects each one, installing the Hermes plugin for you. On a Mac, the Pushary app does the same without a terminal.
How is this different from YOLO mode or auto-approve?
YOLO mode blindly approves everything, including destructive commands. Pushary lets you set per-tool rules: auto-approve safe commands (read, lint, test) and only escalate dangerous ones (rm, git push, deploy) to your phone. You stay in control without the fatigue.
What AI agents work with Pushary?
Pushary works with Claude Code, Codex, Hermes Agent, Cursor, Windsurf, and any MCP-compatible AI agent. Claude Code gets permission hooks and a setup wizard. Hermes gets a native plugin with automatic error notifications.
How do I get notified when Claude Code needs permission?
Install Pushary's hook with one command (npx pushary@latest setup). When Claude Code hits a permission prompt, you get a push notification to approve or deny from your phone. Safe tools can auto-approve so only the decisions that matter reach you.
What are permission hooks?
Permission hooks intercept Claude Code's tool approval prompts and route them through push notifications. When the agent wants to run a command or edit a file, you get a push to approve or deny from your phone. If you do not answer, your rule answers for you, deny or hand back to the terminal.
What is human-in-the-loop for AI agents?
Human-in-the-loop means an AI agent pauses at important or risky steps and waits for a person to decide before it continues. Pushary delivers that decision to your phone as a push notification, so you can keep an autonomous agent moving without watching it and still catch the actions that matter.
What question types does Pushary support?
Three types: confirm (yes/no), select (multiple choice with 2 to 6 options), and input (free text). Your agent picks the right type for the situation.

Why I built this

I kept coming back to an agent that had been waiting the whole time

I would kick off a task, switch to something else, and come back to find the agent had paused for a yes 40 minutes earlier. So I built Pushary to move that decision to my phone. The agent asks, I tap, and the work keeps going while I am away. This is the 2 minute version.

Aadil Ghani · Founder, Pushary

What people running agents tell us

I instantly related with the pain of coming back to my Claude Code and seeing "waiting for your permission" instead of "your task is completed."
Reagan McCullough · AgentPays
Your tool really helped me improve my Cursor workflow and notifies me when the agent needs me or when it has finished a task. I don't know why this problem wasn't solved by someone already.
Andreas Kuoppa · Portality
I love your vision of speeding AI agents up by unblocking the stuck permission screen and eventually learning from your permission behaviour based on the context. This is gonna go big very soon.
Takanari · AI Plaza

Send the next yes to your phone.

The next long task can finish while you are away. One tap and the agent keeps working.

Start your trial

$9.99/mo after a 3-day free trial. Cancel anytime.

Pushary sends the step that needs you, not your codebase.

Building an AI agent for your own customers? Let them approve what it does, from their phone. See Pushary for agent builders

Works with your agent

Stay in control

Guides

Running e-commerce or marketing?Explore push notifications

Unblock your agent.

Start your trial