bigarrow
A visual feedback tool for Mac that converts screen coordinates output by an AI agent into visible arrow hints. It serves as a visual guidance layer between the agent and the human and does not take over click operations.
Timeline (last 90 days)
bigarrow is a Mac application whose core function is to turn coordinates output by an AI Agent into a visible arrow prompt on the screen; after the arrow appears, a human performs the click, and the arrow then disappears.
bigarrow is positioned as a visual feedback layer; it does not do the Agent's own work, nor does it take over the user's click operations.
bigarrow supports Claude Code, Codex, and any AI Agent that can output coordinates.
bigarrow supports multiple monitors and can work across several screens.
bigarrow is free for personal use, and the Pro features cost 9.99 USD as a one-time purchase, with no subscription.
bigarrow only supports Mac and relies on macOS-specific screen overlay and coordinate tracking APIs; there is currently no Windows or Linux version.
bigarrow uses a special macOS window that is borderless, has a transparent background, and does not receive mouse events (click-through) to draw arrows, so the arrow does not block normal click operations when it appears.
Before tools like bigarrow appeared, there were usually two paths for AI Agents to interact with the screen: directly calling system accessibility APIs to perform the click themselves (invisible to humans), or describing the location in natural language and letting a human find and click it themselves.
In the developer's testing, bigarrow ran continuously in the background for a week with no lag, abnormal power consumption, or conflicts with other applications.
bigarrow's auto-detection locates elements based on the Agent's description, but it is not always accurate, and sometimes the arrow points to the wrong position.
4 more timeline events
All Facts (14)
bigarrow is suited to users who treat AI Agents as production tools, such as developers who use AI coding Agents daily, teams that need to automate complex UI workflows, users who value privacy and require local processing, developers who use multiple monitors, and teams that need to audit AI decisions and retain visual evidence.
50%Unverifiedbigarrow is positioned as a visual feedback layer; it does not do the Agent's own work, nor does it take over the user's click operations.
50%Unverifiedbigarrow supports Claude Code, Codex, and any AI Agent that can output coordinates.
50%Unverifiedbigarrow supports multiple monitors and can work across several screens.
50%Unverifiedbigarrow is free for personal use, and the Pro features cost 9.99 USD as a one-time purchase, with no subscription.
50%Unverifiedbigarrow only supports Mac and relies on macOS-specific screen overlay and coordinate tracking APIs; there is currently no Windows or Linux version.
50%Unverifiedbigarrow uses a special macOS window that is borderless, has a transparent background, and does not receive mouse events (click-through) to draw arrows, so the arrow does not block normal click operations when it appears.
50%UnverifiedBefore tools like bigarrow appeared, there were usually two paths for AI Agents to interact with the screen: directly calling system accessibility APIs to perform the click themselves (invisible to humans), or describing the location in natural language and letting a human find and click it themselves.
50%Unverifiedbigarrow is a Mac application whose core function is to turn coordinates output by an AI Agent into a visible arrow prompt on the screen; after the arrow appears, a human performs the click, and the arrow then disappears.
50%Unverifiedbigarrow's auto-detection locates elements based on the Agent's description, but it is not always accurate, and sometimes the arrow points to the wrong position.
50%UnverifiedIn multi-monitor scenarios, bigarrow occasionally places the arrow on the wrong screen; manually specifying the monitor resolves this.
50%UnverifiedConflicts between bigarrow's keyboard shortcuts and those of other applications are a frequent problem; manual configuration can avoid them but increases operating cost.
50%Unverifiedbigarrow's auto-detection works on simple interfaces but easily points wrong on complex interfaces; the errors mainly come from the Agent-side localization capability, not from bigarrow's drawing step.
50%UnverifiedIn the developer's testing, bigarrow ran continuously in the background for a week with no lag, abnormal power consumption, or conflicts with other applications.
50%