kaviri
New Let your agent film the demo over MCPAgents can film demos over MCP

Your demo video is a build artifact.

kaviri films your web app from a script in your repo. It re-records in CI whenever the product changes, and fails the build when the take films nothing.

cargo install --git https://github.com/kaviridev/kaviri
kaviri record --script examples/hero/take.jsonl --out demo.mp4 CI

Recorded by kaviri from an 18-line script, framed as a Mac. Nobody touched a mouse or chose a camera move.

One Rust binary that brings its own Chromium

GitHub Actions Linux and macOS Any URL MCP for agents Apache 2.0

Why kaviri

Demos go stale. Yours won't.

The UI moves and the video does not, because re-recording means a quiet room, an afternoon and the fourth take of the same mouse path. So the demo quietly lies about the product. kaviri makes the demo something your build produces.

Scripted, not filmed

A take is a JSONL file of ops that lives next to the code it films, reviewed and versioned like everything else.

A camera that directs itself

Zooms and pans come from each op's timestamp and bounding box. You describe what happens, never where to point.

Red when it breaks

A take that films nothing, a selector that moved or a frozen page fails the job, with the line number in the log.

Every format from one script

Presets for README, TikTok, square, landscape and phone, plus macOS, Windows, iPhone and Android frames.

Narration and captions

A spoken voiceover, a music bed that ducks under it, and captions timed to the words, as SRT and VTT or burned in.

Built for agents

An MCP server lets Claude Code, Cursor or any agent explore your app, film a take and look at the result.

How it works

Write the take down. Run it in CI.

  1. Write the take

    Navigate, type, click, wait. Every op records a timestamp and a bounding box, and the camera is derived from them.

  2. Add the workflow

    The action installs ffmpeg and Chromium if the runner has none, records the take and uploads the MP4 as an artifact.

  3. Or run it on your laptop

    Same binary, same script, same video. Your pages never leave your machine.

{"op":"navigate","url":"http://127.0.0.1:8099/"}
{"op":"wait","selector":"#q","timeout_ms":30000}
{"op":"start_recording"}
{"op":"wait","ms":2200}
{"op":"mark","label":"start"}
{"op":"type","selector":"#q","text":"14 Rue Lafayette, Paris"}
{"op":"wait","ms":500}
{"op":"click","selector":"#go"}
{"op":"wait","selector":"li","timeout_ms":15000}
{"op":"wait","ms":1400}
{"op":"mark","label":"tracked"}
{"op":"type","selector":"#q","text":"Kigali Heights, KG 7 Ave"}
{"op":"wait","ms":500}
{"op":"click","selector":"#go"}
{"op":"wait","ms":1800}
{"op":"mark","label":"second"}
{"op":"wait","ms":1600}
{"op":"stop_recording"}

The part that matters

The build fails if the take filmed nothing.

A valid MP4 of a Chrome error page passes every duration check. So kaviri compares the first frame with the last. A script that navigates, clicks and types cannot produce the same picture twice.

  • Frozen or blank takes turn the job red, not green.
  • A selector that moved fails with the line and the selector, which is what a CI log needs.
  • A take cut short is refused before it runs, so the last zoom is never chopped off.

Phones, too

Film the mobile view with one line.

Add a frame op and the take is shot at an iPhone's viewport, scale and user agent, inside the bezel, with a tap dot where the finger lands. No simulator, no cable, no phone on a desk.

{"op":"frame","platform":"ios"}
  • iOS and Android handsets, or the simulator and emulator windows on a desktop.
  • 9:16 out of the box, sized for TikTok, Reels and Shorts.
  • The same script in CI, so the phone cut is re-recorded with everything else.
astral-sh/uv on GitHub, filmed in an iOS frame from a 23-line script.

Pricing

The recorder is free. The queue is the product.

Everything that makes the video is open source, with no revenue threshold and no field-of-use limit. The hosted service is a convenience.

Local

For your laptop and your own CI.

Free forever, Apache 2.0

  • One Rust binary for Linux and macOS
  • Drives its own browser over CDP, no screen recorder
  • GitHub Action included
  • MCP server, narration and captions
  • No account, your pages never leave your machine
Read the source

Hosted Beta in December

The same recorder, with the parts you would otherwise build.

Usage per render minute

  • A queue, so a take never occupies a CI minute
  • A stable URL for your README and landing page
  • Every take kept, three releases back and more
  • A preview video on every pull request
Join the beta waitlist

FAQ

Questions, answered

Does it work with my app?

If a Chromium can open it, yes: a localhost dev server, a staging deploy or production. kaviri drives its own browser over the DevTools protocol, so there is no screen recorder, no OS permission and no Wayland portal involved.

How is it different from a screen recorder?

A screen recorder films what a person did once. kaviri films a script, so the same take is made again on every commit, with no display, no mouse and no quiet room. The zooms and pans come from the interactions in the script instead of an editing pass.

How do I record a demo video in GitHub Actions?

Start your app in the workflow, then add uses: kaviridev/kaviri@v1 with the path to your script. The action installs ffmpeg and a browser, builds kaviri, records the take and uploads the MP4 as an artifact. The CI guide has the whole workflow.

Can it film the mobile version of my site?

Yes. One frame op films the take at an iPhone or Android phone's viewport, scale and user agent, inside the device bezel, in 9:16. It is a phone-sized browser, not a native app recorder.

Do I need the hosted service?

No. The recorder is the whole product and runs on your laptop or in your own CI. The hosted service saves you the CI minutes, the storage and the stable URL.

What does the video look like?

An H.264 MP4, captured at twice the resolution so text is sharp, with a drawn cursor, a backdrop and eased zooms. Presets size it for a README, TikTok, square, landscape or phone.

Can an AI agent use it?

Yes. kaviri mcp is a Model Context Protocol server: an agent can open your app, look at what is on screen, film a take and check the poster frame. There is also a plain-text protocol for agents with a shell.

Is it really open source?

Apache 2.0, unconditionally. Fork it, ship it inside your own tool, sell the result. The only thing the licence holds back is the name.

What does kaviri mean?

It is ChiShona for "twice, a second time", said ka-VEE-ree. The demo is not re-recorded. It is made again.

Hosted beta

Ship a demo that never goes stale.

The hosted beta opens in December. Join the list for five short emails on getting the most out of the free recorder, then one when the beta is ready.

No spam. One click gets you off all of it.