stablyai/orca

Computer Use enables an agent to inspect and operate local desktop app windows through accessibility trees, screenshots, and safe UI actions such as clicking controls, typing, pressing keys, scrolling, dragging, and setting values. Use it for interacting with desktop apps, browser windows, webviews, and Orca's own UI.

Linear Tickets lets agents read linked ticket context, post completion updates, move Linear workflow states, attach PR/MR links, and triage Linear tasks using Orca's Linear CLI. Use it when working from a Linear issue, finishing work with a PR/MR, moving status, searching issues, or creating follow-up tickets.

Orca CLI controls Orca-managed worktrees, terminals, repos, automations, artifacts, comments, and the embedded browser. Use it for handoffs, child worktrees, terminal control, artifacts, or controlling the Orca browser.

Orca Emulator controls a mobile iOS emulator/simulator from inside Orca via the orca CLI, including taps, gestures, typing, hardware buttons, camera injection, permissions, and the accessibility tree. Use it when driving the live emulator pane for agent tasks instead of raw serve-sim or simctl.

Orca Emulator Android controls an adb-connected Android emulator or device from inside Orca using the orca CLI. Use it for listing and booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the accessibility tree, and logcat.

Orca Linear uses the Orca Linear CLI to read linked Linear ticket context, post completion updates, move workflow states, attach PR/MR links, and triage Linear issues without treating ticket text as instructions. Use it when working from a Linear issue, finishing work with a PR/MR, moving Linear status, searching Linear issues, or creating follow-up tickets.

Orca Orchestration coordinates structured multi-agent work through threaded messages, blocking ask/reply flows, task dispatch, waits, task DAGs, decision gates, and coordinator loops. Use it when you need to supervise, monitor, wait for results, or decompose work across agents rather than hand off full ownership.

Orca Per-Workspace Environments sets up, reviews, debugs, and validates disposable per-workspace runtimes (cloud sandboxes, VMs, or local) using Orca's version-matched guide. Use it to stand up environments, fix `environmentRecipes` in `orca.yaml`, scaffold lifecycle scripts, or resolve `orca vm recipe doctor` failures.