Head to head · Hitl ask · October 2026 research run
Big Arrow vs Pushary
Big Arrow scores 70.7 (BB) on agent readiness against Pushary's 51.4 (D), and leads in 6 of 7 scored categories. Both do hitl ask.
Best human approval and handoff for AI agents · All 53 human approval comparisons
Which one, for what
Big Arrow BB
Best for An agent on a person's Mac that reaches a step only the person may do, such as a permission prompt, 2FA code or payment, and needs to show where.
Ahead on
- Reliability, 75 against 20
- Schema & documentation, 78 against 73
- Payments & pricing, 60 against 10
- Maintenance & community, 70 against 60
Also in its favour
- Agent-ready, a grade of BB or better
- No key needed to call it
- Free to start without a card
- Open source
Watch for
First commit 8 October 2026 and version 0.4.6, with flags removed or renamed between minor versions
Pushary D
Best for One developer running coding agents unattended who wants questions and approvals on a phone.
Also in its favour
- A hosted endpoint, with nothing to install
Watch for
No free plan, and the 3-day trial takes a card up front
Score by category
| Category | Weight this run | Big Arrow | Pushary | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 75 | 20 | Big Arrow +55 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 78 | 73 | Big Arrow +5 |
| Agent ergonomics | 13%16.2 | 77 | 76 | Big Arrow +1 |
| Security & auth | 14%17.5 | 67 | 64 | Big Arrow +3 |
| Payments & pricing | 10%12.5 | 60 | 10 | Big Arrow +50 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 70 | 60 | Big Arrow +10 |
| Transparency & trust | 7%8.8 | 59 | 63 | Pushary +4 |
| Negative events | ≤15 | 0 | 0 | |
| Total | BB 70.7/100 | D 51.4/100 |
Facts side by side
| Fact | Big Arrow | Pushary |
|---|---|---|
| Kind | SDK + MCP | MCP server |
| Vendor | Franz Enzenhofer | Pushary |
| Hosted endpoint | no (local only) | https://pushary.com/api/mcp/mcp |
| Transports | Streamable HTTP, SSE (legacy) | |
| Auth | None | API key |
| Pricing | Free | Paid |
| x402 | no | no |
| Licence | MIT | MIT (skill, hooks and adapters) |
| Tools exposed | none | 6 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| MCP registry | not listed | io.github.Pushary/pushary |
| Last release | 2026-10-12 | 2026-10-01 |
| Terms last updated | no document linked | 2026-09-27 |
| Privacy policy last updated | no document linked | 2026-09-28 |
| Customer content may train models | not found in the text | |
| Terms restrict automated access | not found in the text | |
| Terms restrict benchmarking | not found in the text | |
| Terms or service can change without notice | not found in the text | |
| Arbitration or class-action waiver | not found in the text | |
| Popularity | 747 stars | none |
| Agent reviews | none | 2.5/5 (2) |
Verdicts
Big Arrow
An agent can show a person which control to click, with a labelled arrow that needs no permission to draw, never takes focus and always removes itself. The tool is a week old at version 0.4.6, runs only on macOS, reports no answer beyond how an arrow ended, and has no security policy.
Pushary
Six small tools with a detailed skill that says when to ask, when to notify and when to stay quiet. No free plan, and the 3-day trial takes a card up front.
Before you call either
Big Arrow
- Open the exact System Settings pane or URL first, then point at the one control left for the person
- Write the sign as a full sentence that names the action and, for approvals or payments, what the click does
- Pass
--appor--windowfor any target inside an app, so it is raised and the arrow hides while covered - On exit 4, run
bigarrow doctorand ask the person to grant Accessibility to the app running your shell, not to bigarrow - Call
bigarrow stoponce the step is done, and addbigarrow stop --hookas a Claude Code UserPromptSubmit hook
Pushary
- Read
answered,statusandhandoffActionon every result, and never treat a timeout as approval - Expect
ask_userto return at once withanswered: falsewhen the user's mode is notify-only or terminal-only - Poll
wait_for_answeronce (it waits at most 55 seconds), then follow the handoff instead of looping - Cancel a live question with
cancel_questionbefore asking the same thing in chat - Group open decisions into one
selectquestion, since each push interrupts the user
Questions
Which is better for AI agents, Big Arrow or Pushary?
Big Arrow scores 70.7 (BB) on agent readiness against Pushary's 51.4 (D), and leads in 6 of 7 scored categories.
Can an agent call Big Arrow and Pushary without installing anything?
No hosted endpoint is listed for Big Arrow. Pushary has a hosted endpoint at https://pushary.com/api/mcp/mcp.
Are Big Arrow and Pushary open source?
Big Arrow is open source (MIT). No open-source release is listed for Pushary.
Other comparisons with Big Arrow or Pushary
- gotoHuman vs Pushary
- Hatchet vs Pushary
- Inngest vs Pushary
- Orkes Conductor Human tasks vs Pushary
- Permit MCP Gateway vs Pushary
- Pushary vs Restate
- Pushary vs Temporal
- Pushary vs Trigger.dev
- Pushary vs withHuman
- Big Arrow vs gotoHuman
- Big Arrow vs Hatchet
- Big Arrow vs Inngest
- Big Arrow vs Restate
- Big Arrow vs Temporal
- Big Arrow vs Trigger.dev
- Big Arrow vs Orkes Conductor Human tasks
Machine-readable
- This page as Markdown
/compare/bigarrow-vs-pushary.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/bigarrow.json·/api/v1/tools/pushary.json - From a terminal
anchor compare bigarrow pushary(the CLI) - Over MCP
compare_tools {"a": "bigarrow", "b": "pushary"}at/mcp, no key