Pushary

Honest comparison

Happy mirrors every session.
Pushary governs the decisions.

Happy is a free, open-source mirror of Claude Code and Codex on your phone. Pushary is the cross-vendor control plane: set per-tool rules once, approve only what matters, and keep an exportable audit trail of every decision across every agent.

The real question

If you want a free, open-source, end-to-end-encrypted mirror of Claude Code or Codex on your phone, Happy is excellent. If you want author-once guardrails, an audit trail, and one tool across every agent you run, Pushary is the better fit.

Pushary is for you if:

  • You want per-tool rules: auto-approve safe reads, push on Bash, always deny rm -rf
  • You run more than Claude Code and Codex (Cursor, Hermes, Windsurf, any MCP client)
  • You need an exportable audit trail for a team or compliance
  • You want a kill switch to stop a runaway agent from your phone
  • You prefer to keep your existing CLI and send decisions, not your code

Happy is for you if:

  • You want a free, open-source tool (MIT)
  • You only use Claude Code and Codex
  • You want end-to-end encryption above everything else
  • You want a full real-time mirror of the session, plus voice
  • You are comfortable running the happy CLI instead of claude or codex

Why it matters

Policy beats tapping every prompt

Happy asks you to Allow or Deny each request, and a remembered choice lasts only for that session. Pushary lets you author the rules once: auto-approve safe reads, push on Bash, escalate git push, always deny rm -rf. The phone only buzzes for the decisions that actually matter, and the rule sticks across sessions and machines. That is the difference between babysitting two agents and trusting four.

An audit trail you can actually export

Happy is end-to-end encrypted, which is great for privacy and also means the server cannot produce a queryable record of who approved what. Pushary keeps an immutable, attributed, exportable log of every question and every human decision, across every agent and machine. That is exactly what a team lead or a compliance owner needs, and it is the one thing an encrypted mirror structurally cannot give them.

One layer across every agent

Happy covers Claude Code and Codex. Pushary is one MCP server and one policy that also covers Cursor, Hermes, Windsurf, and any MCP client. One config, one queue, one audit trail, no matter which agent is blocked.

Where Happy wins

Happy is free, open source under the MIT license, and end-to-end encrypted, with a full real-time mirror of your session and voice. If you want an open-source mirror of Claude Code or Codex on your phone and do not need policy or audit, Happy is the better pick. Pushary keeps decisions auditable while redacting and encrypting Pushary-launched transcripts on your machine for the owner's phone and documented compliance recovery before they sync.

Feature comparison

FeaturePusharyHappy
Per-tool permission policies (set rules once)POLICY
Immutable, exportable audit trailAUDIT
Works with Cursor, Hermes, Windsurf (any MCP client)
Works inside Claude Cowork (connector)
Works with Claude Code
Works with Codex
Approve from your phone
Kill switch to stop a runaway agent
Keeps your existing CLI (no wrapper to run)
Encrypts transcripts before upload
Run multiple agents in parallel
Full real-time session mirror + voice
Provider cannot decrypt transcripts
Open source
Price
$9.99/mo
Free (MIT)

Frequently asked questions

What is Happy?

Happy (happy.engineering) is a free, open-source app under the MIT license that lets you control Claude Code and Codex from your phone or the web. It mirrors your session in real time with end-to-end encryption, supports parallel sessions, and adds voice. You run the happy CLI instead of claude or codex, and you bring your own Claude or Codex subscription.

Pushary vs Happy: what is the real difference?

Happy mirrors your whole session to your phone. Pushary prioritizes the decisions that matter under per-tool rules you set once, keeps transcript context encrypted for the owner's phone and documented compliance recovery, and records every question and human decision in an exportable audit trail across every agent.

Is Happy free, and how much is Pushary?

Happy is free and open source under the MIT license. Pushary's Agent plan is $9.99/mo with a 3-day free trial. The paid line is what funds the policy engine, the immutable audit trail, and cross-vendor support beyond Claude Code and Codex.

Which one is more private?

Both are private, in different ways. Happy is end-to-end encrypted, so its relay only ever sees encrypted data, but there is no server-side audit trail to query or export. Pushary splits the paths. Decision text and tool names stay queryable for the audit trail. Pushary-launched transcripts sync by default after local redaction and encryption; the owner's phone can decrypt them, and authorized Pushary compliance admins can recover an exact session for a documented legal obligation. You can disable sync on the agent machine. Happy maximizes provider-inaccessible encryption. Pushary combines encrypted transcripts, compliance recovery, and auditable decisions.

Can I use both Happy and Pushary?

Yes. They are independent. You could run Happy for a full end-to-end-encrypted session mirror and Pushary for per-tool policies, cross-vendor approvals, the kill switch, and the audit trail.

More comparisons

One policy. Every agent. Every decision on record.

Set your guardrails once, approve from your phone, and keep an exportable audit trail. Works with Claude Code, Codex, Cursor, Hermes, and any MCP client. 3-day free trial.