Windows CI / windows ([bun run --cwd packages/app-core test bun run --cwd packages/elizaos test bun run --cwd packages/cloud/shared test], app-and-cli) (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/scenario-runner test bun run --cwd packages/vault test bun run --cwd packages/security test bun run --cwd plugins/plugin-coding-tools test], framework-packages) (push) Has been cancelled
Windows CI / windows ([bun run --cwd plugins/plugin-elizacloud test bun run --cwd plugins/plugin-discord test bun run --cwd plugins/plugin-anthropic test bun run --cwd plugins/plugin-openai test bun run --cwd plugins/plugin-app-control test bun run --cwd plugins/pl… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run build --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/agent --concurrency=4 node packages/scripts/run-bash-linux-only.mjs scripts/verify-riscv64-buildpaths.sh node packages/scripts/run… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run typecheck --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/cloud-shared --concurrency=4 bun run --cwd packages/core test bun run --cwd packages/shared test], core-runtime, 75) (push) Has been cancelled
Desktop automation plugin for elizaOS agents — screenshots, mouse /
keyboard control, browser CDP automation, window management, clipboard,
and the OCR provider registry that other plugins contribute to.
the OCR provider registries — OcrProvider (line-level) and
CoordOcrProvider (hierarchical with absolute coords), defined in
src/mobile/ocr-provider.ts.
@elizaos/plugin-vision owns the camera pipeline, scene description
via runtime.useModel(IMAGE_DESCRIPTION), the screen tiler, the
detector pipeline (faces / people / objects), and the OCR
implementations themselves. plugin-vision consumes capture from this
plugin via runtime.getService("computeruse") and contributes the
hierarchical OCR adapter into this plugin's registerCoordOcrProvider
seam at boot.
Both seams are runtime feature-detected — neither package depends on
the other.
Enabling
Config: features.computeruse: true
Env: COMPUTER_USE_ENABLED=1
Platform requirements
OS
Capture
Input
macOS
screencapture (built-in)
cliclick (brew install cliclick), AppleScript
Linux
import (ImageMagick) / scrot
xdotool (sudo apt install xdotool)
Windows
PowerShell + System.Drawing
PowerShell
Browser
—
puppeteer-core + Chrome / Edge / Brave
Surface
Actions — COMPUTER_USE (canonical screenshot / click / key /
scroll / etc.), WINDOW (list / focus / arrange / move /...), and
COMPUTER_USE_AGENT (high-level goal-driven autonomous desktop loop:
Brain → Cascade → dispatch up to maxSteps iterations).
Subactions of COMPUTER_USE and WINDOW are promoted to virtual
top-level actions (e.g. COMPUTER_USE_CLICK, WINDOW_FOCUS) so the
planner picks a specific verb directly from the catalogue.
Services — ComputerUseService (serviceType = "computeruse")
and VisionContextProvider.