markupR

You found the bug.
markupR writes it up.

AI writes your code. You still have to review it. markupR records your screen while you talk through what you see, then assembles a structured Markdown document your AI agent can act on immediately.

Download for macOS View on GitHub
Start with
⌘ + ⇧ + F

How it works

You talk. markupR handles the rest.

you
Speak
Say what you see
markupR
Record
Captures your screen automatically
markupR
Assemble
Matches frames to your words
you
Paste
Feed it to your AI agent
⌘⇧F start
talk
⌘⇧F stop
⌘V paste into your agent

Why it matters

Feedback without the friction.

Stop retyping what you already see.

You found the bug. You can see it right there. Now you have to context-switch into writing mode, describe it in text, screenshot it, crop it, drag it into the right spot. markupR lets you just say it. The documentation happens behind you.

You talk at 150 wpm. You type at 60.

A five-minute narration produces more structured output than twenty minutes of writing. And the result is better — markupR places screenshots at the exact moments you were describing something, not wherever you remembered to paste them.

Choose local privacy or cloud convenience.

markupr supports both local Whisper transcription and OpenAI BYOK transcription. Stay fully local when privacy is critical, or use cloud transcription when you want fast setup and reliable results.

Under the hood

Built for developers who read source.

  • Dual transcription paths Use local Whisper for on-device processing, or OpenAI BYOK for fast, reliable post-session transcription.
  • Intelligent frame extraction Records your full screen, then uses transcript timestamps to pull the exact frames that match what you were describing.
  • macOS native Lives in your menu bar. No dock icon. No browser tab. Launches at login if you want it to.
  • Structured Markdown output Sections, headings, and images assembled into a document your tools already understand. Paste into GitHub, feed to Claude Code, drop into Slack.
  • Open source, MIT licensed Read the code, fork it, break it, fix it. No telemetry, no tracking, no analytics.
session-output.md 
## Feedback Session — Feb 5, 2026

### Button sizing issue
The submit button is way too small on mobile.
I'm trying to tap it and keep hitting the cancel
link underneath. Needs more vertical padding,
maybe 12px minimum tap target.
![Screenshot at 0:34](screenshots/fb-001.png)

### Loading state feels janky
After the spinner disappears, the content just
pops in with no transition. There's a visible
layout shift — the sidebar jumps left by about
20 pixels.
![Screenshot at 1:12](screenshots/fb-002.png)

### Nav highlight is wrong
I'm on the Settings page but the Dashboard tab
is still highlighted. Looks like the active state
isn't updating on route change.
![Screenshot at 1:45](screenshots/fb-003.png)

Launch Modes

Same markupr output. Two ways to run it.

markupr open source and markupr premium run the same core pipeline: record screen + narration, transcribe, extract the right frames, and generate agent-ready markdown. Premium is the touchless path with hosted keys preconfigured. BYOK stays fully supported.

Open source (BYOK)

Bring your own OpenAI + Anthropic keys. Full control, same report quality, fully transparent stack.

Premium (touchless)

Exactly the same workflow and output, but keys are hosted for you. No API setup screens, no key management.

Switch anytime

Start with BYOK tonight, move to premium when you want convenience. No workflow migration required.

Use BYOK Open Source Get Premium Access

Launch plan: both BYOK and premium are available on day one. Premium is convenience, not extra capability.