gitwtfhub

wtf is computer-use-capture?

obinnanwachukwu1/computer-use-capture — explained in plain English

Analysis updated 2026-05-18

0SwiftAudience · developerComplexity · 4/5Setup · hard

TL;DR

A macOS tool that records an AI agent's Computer Use session and turns it into a polished, edited product demo video automatically.

Mindmap

mindmap
  root((computer-use-capture))
    What it does
      Records AI agent sessions
      Rebuilds clean timeline
      Renders polished video
    Tech stack
      Swift
      Node.js
      ScreenCaptureKit
    Use cases
      Auto generated demos
      Corrected re renders
      Local only processing
    Audience
      Codex developers
    Setup
      Install via npx
      Grant macOS permissions
      Restart Codex

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Automatically record and edit a polished demo video while an AI agent completes a task on screen.

REASON 2

Ask Codex in plain language to demo a feature in an app and receive a finished video link.

REASON 3

Re-render a completed demo with a corrected cursor, background, or motion setting.

REASON 4

Discard or cancel recordings and renders that are no longer needed.

What's in the stack?

SwiftNode.jsScreenCaptureKitMCP

How it stacks up

obinnanwachukwu1/computer-use-captureaiduckman/claudeusage_latest_may2026arnabau/thermalpulse
Stars000
LanguageSwiftSwiftSwift
Setup difficultyhardeasymoderate
Complexity4/52/53/5
Audiencedevelopervibe coderdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · hard Time to first run · 1h+

Requires Apple Silicon macOS, Codex with Computer Use, Node.js, and granting Screen Recording and Accessibility permissions before recording works.

Wtf does this do

Computer Use Capture is a Mac only tool that turns a Codex Computer Use session, where an AI agent controls your computer to complete a task, into a polished, professional looking product demo video. While the AI is clicking around and performing a task on screen, this tool records it, then rebuilds a clean version of what actually happened and renders it as a smooth 60 frames per second video, complete with a native Mac cursor, gentle camera movement, motion blur, and the boring waiting time cut out. It does not replace or interfere with how the AI performs its task. Instead it runs as a separate local helper program that Codex can call on to start recording, stop recording, and manage the resulting video. Because it runs as one shared background service, a recording started during one task stays visible even if Codex restarts its own connection partway through. To use it, a developer installs it through a single command that adds it to Codex, then simply asks Codex, in plain language, to record a demo of some task in an app like Safari. Codex is expected to check that recording is possible, start the recording once the right screen is ready, perform the task normally, stop the recording, wait for the video to finish rendering, and then hand back a link to the finished file. Several small commands exist under the hood for checking readiness, starting and stopping recordings, checking on a render's progress, requesting a specific correction to a finished render, canceling a render, or permanently deleting a recording. The tool is careful about only showing what it can verify actually happened. If it cannot confirm exactly where a click landed, it renders that moment without a visible cursor rather than guessing its position. Recordings are limited to a single selected app window, and moving or resizing that window mid recording is not supported. There is no audio capture, only video. Everything, including capturing, processing, and rendering, happens locally on the user's own Mac, with recordings and their related files stored in a folder under the user's Application Support directory until the user deletes them. It requires Apple Silicon, a recent version of macOS, Node.js, and screen recording and accessibility permissions to work.

Yoink these prompts

Prompt 1
Help me install and register Computer Use Capture as an MCP server for Codex.
Prompt 2
Write a Codex instruction that records a product demo of a specific app using this recorder.
Prompt 3
Explain what screen recording and accessibility permissions this tool needs and why.
Prompt 4
Show me how to change the background and cursor used in a finished render with recorder_edit.

Frequently asked questions

wtf is computer-use-capture?

A macOS tool that records an AI agent's Computer Use session and turns it into a polished, edited product demo video automatically.

What language is computer-use-capture written in?

Mainly Swift. The stack also includes Swift, Node.js, ScreenCaptureKit.

How hard is computer-use-capture to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is computer-use-capture for?

Mainly developer.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.