Approve Your AI Agents From Your Phone | Pushary

3 min read Original article ↗

Your agent froze on one yes.

It stopped the second it needed permission. One tap on your phone and it keeps working.

Your code never leaves your machine. Pushary sends decisions, not transcripts.

Works with

Claude CodeCodexHermesCursor

Hacker NewsFeatured on Hacker News

What is Pushary?

Pushary is the control panel for AI agents. When your agent needs permission, the question lands on your phone as a push notification. You tap, it keeps working. Works with Claude Code, Codex, Cursor, Hermes, Windsurf, and any MCP agent.

You already know this feeling

You hand off a task, finally stop babysitting it, and come back to find it stuck on a single question.

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.

How it works

How an approval works

No new workflow to learn. The decision just moves from wherever your agent runs to your pocket.

See the whole flow

One approval, start to finish, in under 90 seconds.

Integrations

Decisions in Slack and n8n too

The same question can reach Slack or an n8n workflow. Answer in one place and every other place updates.

Slack. Your agent's question lands in Slack with Approve and Deny buttons. One click answers it, and the message updates with the result.

n8n. One node adds a human checkpoint to any workflow. The flow pauses, asks you, and continues with your answer.

Stay in control

Set the rules once. Approve only what matters.

Risky steps come to your phone. Safe ones run on their own. You set the rules once instead of answering every question.

Auto-approve the safe stuff

Low-risk, reversible steps. Set the allowlist once and stop seeing them.

Escalate the risky ones

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 answers for you, deny or hand back to the terminal.

This is not blanket auto-approve. The actions that can hurt you still need a tap.

Your agent control panel

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

One command. Done.

Pick your agent and run it. Setup takes under two minutes.

Configures MCP server, permission hooks, event tracking, and API key.

What people running agents tell us

Recurring themes from feedback since launch, paraphrased.

On staying unblocked
The agent asks, I tap approve on my phone, and it keeps moving. Nothing sits waiting on me anymore.
On babysitting
I kicked off a job before lunch and actually left. It asked one question, I tapped, and it was done when I got back.
On approval fatigue
Only the risky steps reach my phone now. The safe ones stopped pinging me, and I set that up once.

Questions, answered

Running e-commerce or marketing?

Pushary also sends push notifications to browsers, with no app to install. Set it up in minutes.

Explore push notifications

Send the next yes to your phone.

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

$9.99/mo after a 7-day free trial. Cancel anytime.

Your source code never touches our servers. Only the question itself is sent, the title, body, and tool name. If you miss a question, your rule answers for you, and the question expires after 10 minutes.