Pushary logo

Pushary

For AI developers: Pushary approves agent requests from your phone so Claude, Cursor, and Gemini CLI keep running without manual terminal intervention.

Built by Aadil Ghani · Artificial Intelligence · Productivity · Developer Tools · Freemium

Visit website

In category: #111 of 1985 · Artificial Intelligence

Pushary is a Product Hunt listing on Launch Llama with 401 total upvotes, founded by Aadil Ghani who joined in Jul 2026, compared against 6 alternatives.

Product Hunt listing

Listing status

401upvotes

Community score

Aadil Ghani (Joined Jul 2026)

Founder

Launched on Launch Llama Jul 28, 2026 · #20 of 67 that day

Pushary

About

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.

Follow Pushary: X (Twitter)

Launch Llama's Take

Based on Launch Llama data as of

Pushary has 401 upvotes, including the votes it received on Product Hunt, which ranks it #111 of 1,985 Artificial Intelligence tools on Launch Llama by upvotes, in the top 10%. It has been listed on Launch Llama since July 2026. No Launch Llama members have upvoted it yet and it has no reviews yet.

Pushary sends AI agent approval requests to your phone as push notifications, while CrewTower shows permission requests in the MacBook notch. Pushary's per-tool policies auto-approve safe reads, and every decision lands in an audit trail.

Key Features

  • Send AI agent approval requests to your phone as push notifications
  • Set per-tool rules to auto-approve safe steps and escalate risky ones
  • Deliver decisions to your phone, Mac, Slack, or web app
  • Maintain an audit trail of all agent decisions and actions
  • Support confirm, select, and input question types

Use Cases

  • Developers running Claude Code who want to approve file changes and command executions from their phone
  • Teams building n8n workflows who need human checkpoints without stopping the entire flow
  • Agent builders embedding approvals in their product for end-users

Who it is for

  • AI developers who run coding agents such as Claude Code, Codex, or Cursor from the terminal.
  • Developers building or operating MCP-connected agents who need human approval for sensitive actions.

Pricing

Free 3-day trial. Agent plan $9.99/month with 5K notifications. Agent Pro $19.99/month with unlimited notifications. Team plan $59.99/month for up to 10 members. Partner plans from $99-$799/month for embedding approvals.

View Pushary pricing →

FAQ

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.

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 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 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.

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 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.

Which Pushary plan is for my own agents?

Choose Agent, Pro or Team to get notifications and answer supported approvals from your own coding agents. Choose Partner when you are building approval requests into a product for your customers.

How long is the Agent or Partner trial?

Paid Agent and Partner plans start with a 3-day free trial. Partner trials have lower usage limits than paid plans; the limits and monthly price are shown above before checkout.

Are the Pushary phone and Mac apps included?

Yes. You can use the native iPhone, Android and Mac apps with your plan. Browser delivery is also available. Your agent still runs on its host, which must stay online for it to continue.

Do Partner customers need their own paid plan?

No. You pay for the Partner plan. Your customers connect through your link and can use the free Pushary app without a separate Pushary account, subscription or API key.

Founder Guides

Alternatives

Agent CalloutFor developers: Agent Callout adds voice alerts to AI coding agents so you monitor progress without leaving your terminal.Pushable AIFor enterprises: Pushable AI builds no-code AI agents connecting 500+ business apps so you automate customer support, lead qualification, and workflows.Agent IslandFor developers: Agent Island monitors Claude, Codex, Grok, and Cursor sessions locally so you track AI coding progress without telemetry.CrewTowerFor developers: CrewTower monitors AI coding agents in your MacBook notch, showing permission requests with full context so you approve changes without touching terminal.CursorFor developers: Cursor's Composer 2 generates complex code efficiently at $0.50/M input tokens, reducing development time and costs.AgentKeyFor AI agents: AgentKey connects Claude, Codex, and MCP agents to live search, finance, social, and e-commerce data instantly so workflows access real-time information without manual integrations.

Tags

#agent approvals#push notifications#ai coding agents#terminal workflows#auto-approve rules#mobile approvals#audit trail#claude code#cursor users#qr pairing

Ask AI about Pushary

ChatGPT Claude Perplexity Grok