Pushary

Control Claude Code
from your phone.

Approve risky commands, answer questions, and stop a runaway session from your lock screen. You stay in control without sitting at the terminal.

99,9 %Délivré
Hacker NewsMis en avant sur Hacker News
3-4xvs E-mail

You do not need your terminal on your phone

Mirroring your whole terminal to a phone screen is a worse desk. The thing you actually need on the go is the handful of decisions only you can make.

Babysitting the terminal
Sit and watch the agent work
Catch the risky command in time, or miss it
Walk away and it stalls on a question
No record of what you approved
Nothing stops a runaway run
With Pushary on your phone
The agent runs on your machine
Risky commands wait for your tap to approve
Answer a question and it keeps going
Every decision lands in an audit trail
Kill switch stops it in one move

Let Claude Code run. Keep your hand on the controls.

One command to connect. Approve, answer, or stop from your phone.

Frequently asked questions

Can I control Claude Code from my phone?

Yes. With Pushary, Claude Code sends a push notification to your phone when it needs a decision: a risky command to approve, a question to answer, or a task that finished. You respond from your lock screen and the agent continues. You can also stop a running agent with the kill switch.

Does this put my whole terminal on my phone?

No, and that is on purpose. Tools like Happy or Omnara mirror your terminal to your phone so you can type prompts on the go. Pushary does the opposite: it leaves Claude Code running on your machine and sends you only the moments that need a human. You get the decisions, not a tiny terminal.

How do I approve or deny commands from my phone?

Set a permission policy that says which commands need your approval. When Claude Code tries to run one, Pushary pushes it to your phone with Approve and Deny buttons. On Claude Code the command is physically blocked until you answer, so nothing risky runs while you are away.

What if I do not respond?

You decide the timeout and what happens when it passes: keep waiting, deny by default, or fall back to the agent's own prompt. The enforced gate fails closed, so an unanswered risky command does not just run on its own.

Does it work with anything besides Claude Code?

Yes. The same setup works with Codex, Cursor, Hermes, Windsurf, and any MCP client. One permission policy and one audit trail cover every agent you run.

How much does it cost?

Pushary starts at $9.99/month with a 7-day free trial. That includes phone approvals, the permission policy, the audit trail, and 5,000 notifications a month.