Pushary - Approve AI requests from your lock screen
by•
One command connects your AI agents to your lock screen. When Claude Code, Codex, Cursor, Gemini CLI, Hermes, or Claude Cowork stops to ask, you tap yes from your phone and the run keeps moving. New in this launch: native iPhone and Android apps. Pairing is a QR code you scan from the terminal, no key to paste. Per-tool policies auto-approve the safe reads. Every decision lands in an audit trail.
Replies
Pushary
Hey PH 👋 Aadil here.
Pushary is the yes button for your AI agents. Their permission prompts and questions land on your phone's lock screen, you tap, the run keeps moving.
The problem
You hand an agent a 40-minute job and walk away. Two minutes in, it stops to ask permission for something trivial, and the whole run freezes until you wander back to the terminal. You can pay double for faster tokens and the run still waits at the same prompt. The slowest step in an agent run is usually you.
What's new in this launch
If you've seen Pushary here before: the first three versions ran on web push. iPhone web push drops just enough notifications that one missed approval kills trust in the whole setup (launch three got four upvotes, you can look it up). This launch is the rebuild on a channel you can trust:
- Native iPhone and Android apps, with approvals as lock screen actions
- Pairing is a QR code you scan from the terminal, no API key to copy around
- One inbox for every agent and machine you run
What's live today
- Enforced gating for Claude Code, Codex, Gemini CLI, Cursor, and Hermes: a risky command blocks until you answer, instead of pinging you after it already ran
- Claude Cowork and claude.ai connect with one pasted link and ask cooperatively
- Per-tool policies auto-approve the safe reads, so your phone only buzzes when it matters
- Every question and answer lands in an exportable audit trail
How it compares
- Happy and Omnara mirror your whole session to your phone, a terminal in your pocket. Pushary sends only the decisions: approvals, questions, task done. Less to look at, nothing to miss.
- Anthropic's Remote Control is free and genuinely good if you're on Claude Max and only run Claude Code. Pushary covers six agents across vendors and machines from one phone.
- DIY push (ntfy and friends) tells you after the fact. Pushary's hook integration blocks the risky command until you answer.
Where it kicks in
🚶 The agent hits a permission wall mid-refactor. You answer from the sidewalk. It never notices you left.
🍕 Three agents on two machines, one inbox, cleared over lunch.
🌙 The overnight run that used to die at 2am on a yes/no question.
Honest bits
$9.99/mo after a 7-day trial, and the trial asks for a card up front.
What I'd love from you
Hand your agent something long and tell me where you were when the first question reached your phone. Couch, train, school pickup. And if your agent still ended up waiting on you, that's exactly the feedback I need.
I'll be here all day <3
FetchSandbox
@aadilghani the audit trail angle is what gets me most here. everyone's focused on the "don't let the agent freeze" problem but having an exportable record of every approval decision is actually the compliance story nobody's talking about yet. curious whether you've had enterprise teams ask about that specifically, or is it mostly solo devs right now?
Pushary
@rnagulapalle
this in specific was a team plan request, there were 3 devs working in a team and they wanted a shared export to later pass the approval/deny logic down through a model to learn the positives and negatives of their decision making during their retros.
super smart chaps, you can also use this as a solo dev just to recon on what went right and what went wrong, then feed it to Pushary auto-pilot which further auto approves the obvious commands which makes the agent go faster.
minimalist phone: reduce your screentime
So basically you can manage AI agents from your phone instead of laptop?
Pushary
@busmark_w_nika
Almost. The agent still runs on your laptop or server, you're not coding on your phone. Pushary just reaches you the moment it needs a human, so you can approve, deny, or answer from anywhere and it keeps moving. The phone is where the agent finds you when you've left the desk, not where you do the work.
the bottleneck was never the model, it was the human delaying the nudge, bringing this to the closest interface belonging to a human is the key.
Pushary
@nivotools
Julian, thanks for the support and appreciation. Looking forward to earning you as our user <3
Can Pushary be used as an external Human-in-the-Loop (HITL) service via API?
I'd like my AI agents (built with LangGraph.js, Mastra, or PydanticAI) to send approval requests to Pushary, wait for a human response, and then continue execution.
Does Pushary provide APIs or webhooks that support this workflow?
Pushary
@cvreyher
of course we have dedicated HITL API's with our partner plan, more information here https://pushary.com/human-in-the-loop
simple stupid one line integration.
Pushary
you basically named the exact tension in your own forum post (babysit vs walk away) and this is the fix for it, just across 6 tools instead of 1.
Pushary
had this happen last week actually, agent just sat there for 20 min waiting on a permission.
Pushary
This actually looks very useful. I'm gonna try this out. Does it also work with VSCode and Antigravity?
Pushary
Many other agent-approval tools I tried miss is that risk accumulates across a run rather than sitting in any one command, and I think you guys are on the way to catch that! Also fail-closed gating on the risky call is the genuinely useful bit here. Though does a session carry any notion of its own accumulating blast radius? Congrats on the launch!
Pushary
@artstavenka1
Thanks Art. Today we score risk per command, not per run. The classifier flags the dangerous calls and those always get held for you, on top of the per-tool policies you set.
A session that carries its own accumulating blast radius though, we're not there yet. That's the build, and you've framed it better than I usually do. Would love to compare notes.
ok but is it really worth 10 bucks a month just for tapping yes/no on my phone.
Pushary
@ayazakram
Fair pushback. The tap is the cheap part.
What you're actually paying for is the agent not sitting dead for an hour while you're away from the keyboard. It hits a risky command mid-run, and instead of blocking until you wander back, it reaches your phone and keeps going the second you answer.
It's also one policy across Claude Code, Codex, Cursor and Gemini, so the safe stuff auto-approves and only the calls that genuinely need a human ever buzz you. And every decision lands in an audit trail, which starts mattering the moment more than one person is running agents.
If you're running a single agent and happy watching the terminal yourself, honestly it might not be worth it yet. It earns the $10 the day you stop watching.
what happens if you're on a plane or somewhere dead zone and something's blocking on you.
Pushary
@sadie_charlotte
Good question, and honestly it's the whole point. Nothing risky runs while you're dark. Pushary is fail-closed: no answer defaults to no, so a blocked call never gets auto-approved on your behalf just because you dropped off signal. The worst case is that one step waits or gets denied per the policy you set, while everything safe keeps moving.
And you set that behavior per tool. A risky command can hold for a decision, fall back to deny after a timeout you choose, or route to a teammate if you're out of reach. Meanwhile reads, greps, anything you've allowlisted auto-approve, so most of a run never needs you at all.
When you land, the questions that were waiting are sitting in your inbox. You answer, the agent picks back up.