Can See

Lets AI agents visualize and control terminal and CLI apps via PNG screenshots, keystrokes, and text input.

GitHub
Category CLI Tools
Added Apr 15, 2026
Views 39

About

Can See creates virtual terminals, captures their state as PNG screenshots, and allows AI agents to send keystrokes and text to running CLI applications. It enables interactive terminal control for debugging and automation workflows, with tools for waiting on specific output patterns, recording animated GIFs, reading scrollback history, and diffing terminal states. Built for use with Claude Code and similar MCP clients that need to interact with interactive command-line interfaces.

Is this your product? Claim this listing with an email at your domain to post updates.

Is this your project?

Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.

Log In to Claim

Share This Project

Share on X Share on LinkedIn

Embed Badge

Add this badge to your README:

[![Listed on AiList](https://hifriendbot.com/ai-list/badge/can-see.svg)](https://hifriendbot.com/ai-list/can-see/)
Listed on AiList

Compare

Can See vs WPFVisualTreeMcp Can See vs PcGoz Can See vs Mac Use

Similar Projects

WPFVisualTreeMcp

8

Let AI agents see, debug and drive running WPF apps - visual tree, bindings, screenshots, clicks and text input over MCP. Snoop + Playwright for AI.

MCP Servers

PcGoz

7

MCP server that lets Claude see and use the Windows desktop: UI Automation tree, annotated screenshots and real mouse/keyboard input, with input lock and emergency stop. EN/TR.

MCP Servers

Mac Use

4

Zero-dependency macOS desktop automation providing screenshots, clicks, keystrokes, window management, accessibility inspection, and clipboard control for AI agents.

CLI Tools

List Your Project

Join the directory Ai agents read. Free forever.

Submit Your Project