shotbox

shotbox

[PyPI] [npm] [CI] [Glama]

Eyes, ears and hands on a real graphical program, for an AI agent, a script or CI.

An agent working on a program with a window can't see it or hear it. shotbox runs the program in a sealed session of its own, X11 or Wayland, and lets whatever is driving it look, listen and act: read the accessible tree, take screenshots, record what it plays, click by a button's name, type, hold keys and gamepad buttons, and wait until the program is actually ready. Then measure what it finds: names a screen reader can't say, contrast, the Tab order, pixels changed against a reference, where it flickers, how fast it follows the pointer, where its sound drops out, and what it used. Nothing it runs reaches your desktop or speakers by accident, and with --net loopback, not your network either.

[shotbox finding an unnamed button and faint text and hearing what Orca says of them, comparing pictures, hearing a dropout, catching flicker, driving a game with a gamepad and finding a brittle, blind test]

Made with shotbox: each scene is a play script in a sealed session, recorded by shotbox record. With sound.

claude mcp add shotbox -- shotbox mcp --allow ~/src/app/shotbox-programs

Without an agent, it's the same session from the command line:

shotbox shoot editor.png --window '.*Text Editor' -- gnome-text-editor notes.md

Worked examples, from checking a change to a game's smoke test: docs/recipes.md. How it differs from other tools that drive a GUI: docs/comparison.md.

For agents

shotbox mcp --allow PROGRAMS gives an agent sealed sessions over the Model Context Protocol (stdio). It can start a session, spawn programs from the list in PROGRAMS (NAME = COMMAND a line, and nothing else), and then:

• read the accessible tree, and take screenshots, which come back as images;
• click by a node's name, press keys, type and work a gamepad;
• wait for windows, stillness and announcements;
• lint, measure contrast and walk the Tab order;
• record what a session plays, and hear where it dropped out.

That's enough for an agent to check its own change in a GUI, test a game by playing it, audit what a screen reader hears, or reproduce a bug report in a session that's the same each time. The accessible tree is the cheap way to look, a thousand or two tokens of text; a screenshot is for what only pixels say. An agent can't run anything off the list, and its sessions stop when the server does.

What it's for, the tools, and how it's built: docs/mcp.md.

An agent that runs a program itself, from its shell, runs it on your desktop: a window opens on your screen, a sound plays through your speakers, a browser run under xvfb-run finds your Wayland display all the same. To keep it in a session, put this in the project's CLAUDE.md or AGENTS.md, or your own:

## Graphical programs, browsers and sound
Never run a graphical program, a browser (headless too) or anything thatmakes sound straight on this machine: it reaches my desktop and speakers.Run it in a shotbox session:
- a picture: `shotbox shoot OUT.png --window RE -- COMMAND`- a script or a test suite with windows: `shotbox run [--audio] -- COMMAND`- with none, a headless browser say: `shotbox exec [--audio] -- COMMAND`;  the shotbox package's `sealed()` seals a browser's environment, but  not the speakers- a session to come back to: `shotbox start --name NAME`, then  `shotbox spawn --session NAME -- COMMAND`, and `shotbox stop NAME`
Not `xvfb-run`: it lets `WAYLAND_DISPLAY` and the session bus through. Aserver started for a test listens on 127.0.0.1, not 0.0.0.0.

Why

An agent checking its change, a screenshot for a README, and a test in CI all want the same things, and every project was growing its own copy:

• Sealed. Nothing of yours leaks in by accident, and nothing the program does reaches your desktop or speakers, where bubblewrap can make a sandbox (it says when it can't): What's sealed.
• Ready, not slept. Waits are for things: a window mapped, a port open, a file written, text on a terminal's screen, or the picture holding still. No sleep 6 and hope.
• Deterministic. X11 on Xvfb, GTK's software renderer, LANG=C.UTF-8, TZ=UTC, text carets that don't blink (GTK's, Qt 6.5's, browsers'; and GTK's animations off), GTK 4's text drawn at its color, as its manual font rendering does, not fainter by however much a GTK release's automatic one draws it (more), and PNGs with no timestamps in them. It's the same every time, not the same as a desktop: differences from a desktop.
• Cleaned up. Every program runs in its own process group, and the group is killed on the way out: signalling a wrapper script alone leaves its children running.

Install

On Debian, with what every command and option can use:

sudo apt install xvfb xauth dbus-daemon imagemagick x11-utils python3-gi gir1.2-vte-2.91 \  at-spi2-core gir1.2-atspi-2.0 python3-gi-cairo gir1.2-pango-1.0 libglib2.0-bin pipewire \  wireplumber ffmpeg bubblewrap libfaketimepipx install --system-site-packages shotbox

--system-site-packages lets it see the system's PyGObject, which shotbox term and --a11y use; pip install shotbox works too. Or run it from a checkout: ln -s "$PWD/bin/shotbox" ~/.local/bin/shotbox.

shotbox doctor says what's here and what's missing, a line each, and how to get it. What each command and option needs: Needs.

No Python packages: it's the standard library and those tools. Wayland sessions need more; see Wayland.

In a GitHub Actions job on Ubuntu, the Action installs it and what it runs, as of the release (or branch) it's used at, with what each feature needs asked for by name (all off unless set), and lets bubblewrap make its sandbox, which Ubuntu's AppArmor holds back:

- uses: mishan/[email protected]  with:    a11y: true        # --a11y and `shotbox a11y`    speak: true       # `shotbox a11y speak`: Orca, and what a11y installs    term: true        # `shotbox term`    # wayland, audio, record, gamepads and clock too- run: shotbox shoot app.png --window 'My App' -- ./my-app

A quick tour

shotbox shoot app.png --window 'My App' -- ./my-app          # a picture, once it's upshotbox shoot app.png --twice --window 'My App' -- ./my-app  # the same every time?shotbox compare ref.png app.png --diff diff.png              # what changed, and whereshotbox run -- ./take-pictures.sh       # a script that waits, clicks and captures insideshotbox exec --audio -- npx playwright test        # sealed, with no displayshotbox start --name ed --a11y          # a session to come back toshotbox spawn --session ed -- gnome-text-editorshotbox --session ed a11y click Openshotbox --session ed capture open.pngshotbox stop ed

Commands

The options sessions take, --wayland, --a11y, --audio, --gamepads, --net loopback, --identity, --clock, --dark and the rest: Session options.

What's sealed

A session keeps a program from reaching your desktop by accident, not one that sets out to:

• Its environment is rebuilt from an allowlist; HOME and every XDG directory are a scratch dir.
• Its display, session bus and system bus, and with --a11y and --audio its accessibility bus and sound server, are its own; the sound server plays to nowhere. It has no printers (but CUPS on localhost:631, unless --net loopback). --machine-bus gives it the machine's system bus and printers.
• Where bubblewrap can make a sandbox (it says when it can't), nothing reaches the machine's sound devices or your desktop's Wayland, PulseAudio, PipeWire and bus sockets.
• Your network is reachable unless --net loopback, your user and host name show unless --identity, and the real time unless --clock.
• Not sealed: the files outside the scratch home, your X server, and other processes.

All of it, and what each option covers and doesn't: docs/sealed.md.

Accessibility

--a11y starts an accessibility (AT-SPI) bus of the session's own, so what a screen reader would hear can be read and checked. Without it, a session has none: GTK is told not to look. Your desktop's bus is never touched either way.

shotbox a11y prints the tree, lints it for what has no name to say, walks the Tab order, clicks by name and measures contrast, shotbox wait announce waits for what's announced, and shotbox wait node for a node to show; for GTK, Qt, AccessKit's toolkits and Chromium. The commands, how it's put together, and what each check can and can't tell: docs/accessibility.md.

Wayland

--wayland makes a session a Wayland one: the program runs under a headless sway, drawing in software, instead of on Xvfb. --xwayland adds an Xwayland to it, and DISPLAY, so an X client runs the way it does on a Wayland desktop, GTK programs made to with --env GDK_BACKEND=x11.

Needs sway and grim, Xwayland for --xwayland, and wf-recorder for record: sudo apt install sway grim xwayland wf-recorder. Why sway, how it fits, and what differs from X11: docs/wayland.md.

Docs

• Commands: every command and session option, what each needs, resource use and the clock
• What's sealed
• Recipes: worked examples
• How it compares with other tools that drive a GUI
• MCP: the tools an agent gets, and how they're built
• Accessibility
• Wayland
• Differences from a desktop: drawing, window manager, animations, language, scale, input, measurements
• Gamepads
• Python: shotbox.Session and here(), for a script that drives the display itself
• Node: helpers for browser checks with Playwright
• Mutation testing: shotbox mutate, its changes, verdicts and limits
• Contributing: the tests
• Code of conduct, security and accessibility
• Releasing
• Changelog

License

MIT. See LICENSE.