Show HN: Agent-screenplay – Create beautiful screen recordings with one prompt

Developer Georgi Petrov released Agent-screenplay, an open-source npm package (`agent-screenplay`) that lets AI coding agents such as Claude Code, Codex and Cursor write a JSON "scenario" and have it filmed and edited into a polished screen recording. Screenplay contains no AI model itself and requires no model key — the agent does the planning while the tool handles browser or desktop-app capture and Screen Studio-style editing (smooth cursor, automatic zooms, callouts, captions, title cards and optional voice-over) at 1920×1080 and 30 fps by default, up to 4K and 24–60 fps. It installs via `npx agent-screenplay init`, which downloads Chromium once and registers an MCP server with detected agents, and requires Node 20+.

screenplay-intro-final-v2.mp4 Create beautiful screen recordings with one prompt. Any website, yours or someone else's, or any desktop app. Works with Claude Code, Codex, Cursor and any MCP client. Ask your agent: "Make a video that shows how human handoff works" . The agent explores the site or app and writes a short scenario ; Screenplay plays it in a browser or a desktop app , films it, and edits the video like Screen Studio would: smooth cursor, automatic zooms that follow the action, click effects, callouts, spotlight, captions, title cards, and an optional voice-over. Screenplay contains no AI and needs no model key: your agent does the thinking, Screenplay does the filming and editing. npx agent-screenplay init The npm package is agent-screenplay ; installed globally npm i -g agent-screenplay , its command is screenplay . init downloads Chromium once , adds the Screenplay MCP server to the agents it finds Claude Code, Codex, Cursor , and installs the guide that teaches them to make good videos. Restart your agent after it. In Claude Code , type /screenplay and say what you want: /screenplay Make a 30-second walkthrough of https://askli.co /screenplay Film how to invite a teammate in our app, with a French voice-over In Codex, Cursor or any agent with the MCP server, just ask: "Make a screen recording of …" . The agent explores the site, asks whether you want a voice-over, writes the scenario, films it, checks the storyboard and gives you the MP4. To change the look afterwards: npx agent-screenplay style <scenario.json . Without MCP, any agent that can run commands can use the CLI directly: npx agent-screenplay guide how to write a good scenario npx agent-screenplay check demo.json plays the steps fast, without filming npx agent-screenplay record demo.json films and edits → demo.mp4 + demo.storyboard.png npx agent-screenplay render demo.json re-edits the last take style, zoom, text, voice without filming Requirements: Node 20+. ffmpeg and the drawing library ship with the package. { "url": "https://app.example.com/inbox", "style": { "background": "dawn" }, "steps": { "title": "Human handoff, in one click", "subtitle": "New in 2.4" }, { "click": "text=Camille Laurent", "say": "When the AI agent gets stuck, the conversation lands in your inbox." }, { "callout": "role=button name='Take over' ", "text": "Take over from the AI agent" }, { "click": "role=button name='Take over' ", "say": "One click, and the conversation is yours." }, { "type": "Hi Camille, I'm on it.", "into": "placeholder=Write a reply…" }, { "click": "role=button name='Send' " }, { "highlight": "text=Assigned to you", "text": "Your teammates see it's yours" }, { "end": "Available today on every plan" } } - Targets name elements the way people see them: text=… , role=button name='…' , label=… , placeholder=… , testid=… , css=… web only , at=x,y desktop apps without accessible elements only . - Actions : goto , click , type , press , hover , scroll , select , wait , pause . - Direction : title and end cards, callout a bubble pointing at an element , highlight spotlight , zoomTo , and on any step say caption and voice , zoom , hold . - Style : background preset soft light gradients: dawn , iris , citrus , apricot , coral , blaze , cloud , glacier , tide , meadow , your own gradient, a color or an image; padding, corner radius, shadow, the cursor arrow by default, a rounded arrow in the accent color; macos , dot and its click effect ripple by default; rays , confetti , sparkle , maximum zoom, browser frame, accent color. See Style style . - Output : 1920×1080 at 30 fps by default; any size up to 4K, 24 to 60 fps, optional GIF. The full format is the JSON schema in schema/scenario.schema.json https://github.com/gmpetrov/agent-screenplay/blob/main/schema/scenario.schema.json npx agent-screenplay schema , and the agent guide in skills/screenplay/SKILL.md https://github.com/gmpetrov/agent-screenplay/blob/main/skills/screenplay/SKILL.md . Examples are in examples/ https://github.com/gmpetrov/agent-screenplay/blob/main/examples . check and record really perform the steps a "Send" click sends : point scenarios at a demo account or a staging environment. Set the look by eye: npx agent-screenplay style demo.json opens an editor in your browser, on a frame of the last recording. Pick a gradient or make your own , a color or an image drop it on the page , set the padding, corners and shadow, then save to this video or to all videos , and render without filming again. "All videos" writes screenplay.config.json , which applies to every scenario in its folder and below; a scenario's own style wins, setting by setting. The same settings by hand: { "style": { "background": { "gradient": " 0ea5e9", " 6366f1" , "angle": 135 }, "padding": 96, "radius": 20, "shadow": true } } Title and end cards title and end steps are off by default : turn them on with "cards": true , or with the switch in the editor. background is a preset name dawn by default; earlier presets such as aurora or ocean still work , a color " 0f172a" , an image path relative to the file that sets it , or { "gradient": 2 to 4 colors , "angle": degrees } . - npx agent-screenplay login https://app.example.com opens a browser window: sign in, then close the window . The session is saved to .screenplay/auth.json while you go, and when the window closes; Enter in the terminal works too . Use it with "auth": { "storageState": ".screenplay/auth.json" } . Keep that file out of git. - Bot checks Cloudflare's "Just a moment…" : Screenplay's browser presents itself as an ordinary Chrome, so the checks that need no person pass by themselves. When a site asks a person to prove they are human, check says so: run login on that site, pass the check in the window, close it, and set auth.storageState . Some sites ask again on every visit; those cannot be filmed automatically. - Agents without a screen can sign in with steps: { "type": "${EMAIL}", "into": "label=Email" } , { "type": "${PASSWORD}", "into": "label=Password", "secret": true } . ${VAR} is read from the environment; secret masks the text in captions and logs. Off by default. Turn it on per scenario: "voice": { "enabled": true, "language": "fr" } Each step's say is spoken, and the video waits for each sentence to finish, so the voice sets the pace. Three ways to get the voice: - Cartesia https://cartesia.ai : set CARTESIA API KEY . - ElevenLabs https://elevenlabs.io : set ELEVENLABS API KEY . When both keys are set, Cartesia is used unless "provider": "elevenlabs" . - Your own audio files , with no key: give a step "audio": "voice/02.mp3" MP3, WAV, M4A… , for instance lines you generated in ElevenLabs' or Cartesia's web app, or with a local TTS model Piper, Kokoro… that your agent runs for you. The agent can write the narration for you, one line per step, ready to paste there. Adding audio needs no new filming: render . Narration is cached: re-rendering with unchanged text costs nothing. voice.id picks another voice, voice.speed its pace. Without voice, say still shows as a caption. Use "app": "<name " instead of "url" . The steps are played through the operating system's accessibility APIs by agent-desktop https://github.com/vercel-labs/agent-desktop installed with Screenplay , and the window is filmed with ffmpeg without the system cursor; the editing is the same as for websites. | | Needs | |---|---| | macOS | Allow your terminal or agent app in System Settings → Privacy & Security → Screen Recording and Accessibility | | Windows | Nothing | | Linux | An X11 session with the AT-SPI accessibility bus standard on GNOME . Wayland is not supported: it blocks screen capture and synthetic input by design | Desktop recordings need a real screen: they cannot run in a headless container. Websites can. While Screenplay drives the computer, a pill at the top of the screen says so "Screenplay is recording", or "rehearsing" during a check , with a Stop button that ends the run at once. The pill is left out of the capture, so it is never in the video. macOS and Windows; SCREENPLAY INDICATOR=0 turns it off. "screen": true films the whole main screen instead of one window, for videos that go from one app to another or use the menu bar. { "open": "<app " } launches an app or brings it to the front, a step's "app" acts in another app, and "surface": "menubar" or menu , sheet , popover , alert finds elements outside the app's window. Everything on screen is filmed, desktop icons and notifications included: tidy the screen first; on macOS "hideOthers": true hides the other apps. scenario.json ──▶ play + film ──────────────────▶ take frames + timeline of actions web: Playwright, headless Chromium │ desktop: agent-desktop + ffmpeg ▼ edit: time remap long waits sped up , camera spring zooms , cursor path, overlays, captions, voice track │ ▼ draw each frame Skia → ffmpeg → MP4 Screenplay knows exactly where and when each click happens, and the box of every element it acts on, so zooms are framed on the element instead of guessed from mouse movement. The cursor is drawn during editing, along a smooth human-like path. npm install npm run build npm test unit tests npm run test:e2e records a real scenario in headless Chromium and talks to the MCP server npm version patch --no-git-tag-version or minor / major; also updates src/version.ts Merge that change, then tag the commit on main: git tag v0.1.4 origin/main && git push origin v0.1.4 The tag starts .github/workflows/release.yml . It checks that the tag matches the version and is on main, runs the tests, publishes to npm with provenance and creates the GitHub release with notes from the merged pull requests. A version like 0.2.0-beta.1 goes to npm's next tag. Creating a release in GitHub's UI with a new tag works too. examples/demo-app is a small web app for trying scenarios; examples/desktop-app/notes.py is a GTK app for desktop recording on Linux. MIT. Bundled: Inter https://rsms.me/inter/ SIL Open Font License , ffmpeg through ffmpeg-static GPL , agent-desktop Apache-2.0 .