Computer Use

Noora Agent can drive your desktop — clicking, typing, scrolling, dragging — in the background on macOS, Windows, and Linux. Your cursor doesn't move, keyboard focus doesn't change, and your virtual desktops / Spaces don't switch on you. You and the agent co-work on the same machine.

Unlike most computer-use integrations, this works with any tool-capable model — Claude, GPT, Gemini, or an open model on a local OpenAI-compatible endpoint. There's no Anthropic-native schema to worry about.

How it works

The built-in computer_use toolset is the recommended Noora integration. It speaks MCP over stdio to cua-driver, an open-source background computer-use driver. Each platform uses the appropriate accessibility + input stack under the hood:

Platform	Accessibility tree	Input dispatch
macOS	AX (private SkyLight SPIs)	`SLPSPostEventRecordTo` — pid-scoped, no cursor warp
Windows	UIAutomation	`SendInput` + `PostMessage` — no focus steal
Linux	AT-SPI (X11 + Wayland)	XTest (X11) / virtual-keyboard (Wayland)

The result is the same on every platform: the agent can read the accessibility tree of any visible window AND post synthesized events without bringing it to front, switching virtual desktops, or moving the real OS cursor.

For the underlying contract — why background mode matters, the no-foreground invariant, click-dispatch internals — see cua.ai/docs/explanation/the-no-foreground-contract.

Enabling

Fresh installs already have the driver. The Noora installer (install.sh / install.ps1) pre-installs cua-driver (best-effort; pass --skip-computer-use / -SkipComputerUse to opt out), so enabling Computer Use is just a config flip:

noora tools → pick 🖱️ Computer Use — installs the driver automatically if it's still missing.
Dashboard / desktop app → toggle the Computer Use toolset — if the driver is missing, the toggle kicks off the install in the background automatically (watch progress in the toolset panel).

Manual fallback (older installs, skipped installer step):

noora computer-use install

This fetches and runs the upstream cua-driver installer — install.sh on macOS/Linux, install.ps1 on Windows. Use noora computer-use status to verify the install.

Already have cua-driver? Noora reuses it when it supports the 0.20 runtime contract. During setup, toolset enablement, noora update, and the first computer_use call of a session, Noora checks the local version and manifest. It repairs an old or incomplete standard installation through the upstream installer (at most once per session at runtime). A binary selected with NOORA_CUA_DRIVER_CMD stays under your control, so Noora reports the incompatibility and leaves it unchanged.

If you install Cua Driver first, cua-driver skills install installs Cua's skill pack under ~/.cua-driver/skills/cua-driver. Noora autodetection is a planned cua-driver follow-up, so currently point Noora at that directory or symlink it into your skill space. You can also register raw Cua MCP tools as a custom MCP server, but that is an alternative for users who need the low-level interface. The built-in toolset provides Noora actions, configuration, approvals, and diagnostics.

After installing, regardless of which path you took, grant the platform-appropriate prereqs:

Platform	Prereqs
macOS	System Settings → Privacy & Security → Accessibility + Screen Recording. Grant the identity named by `noora computer-use doctor`. Standard mode uses CuaDriver.app; bounded and unrestricted modes use the Noora host identity.
Windows	None at install time. If you're driving over SSH (not RDP / console), you need the autostart pattern — see cua.ai/docs/how-to-guides/driver/windows-ssh for the Session 0 ↔ Session 1+ proxy.
Linux	A reachable display server: `DISPLAY` set for X11, or `XDG_SESSION_TYPE=wayland`. Wayland sessions need an XWayland bridge for capture. AT-SPI must be on (default on GNOME/KDE/Xfce).

Then start a session with the toolset enabled:

noora -t computer_use chat

or add computer_use to your enabled toolsets in ~/.noora/config.yaml.

Permission modes and logged-in browser profiles

Noora maps its existing approval UX onto cua-driver's immutable runtime modes. Permission mode, capability manifest approval, and the existing-profile grant are launch settings. They cannot change after the runtime starts:

Noora session	cua-driver mode	Human intervention	`existing_profile`
Manual or smart approvals (default)	`standard`	Normal Noora approvals; Cua stops at its protected boundary	Refuses unless `computer_use.grant_existing_profile: true` (one-time config opt-in)
`computer_use.permission_mode: bounded` + reviewed manifest	private `bounded` daemon	You review and approve the capability manifest once, at launch	Allowed only within the manifest's declared profiles/origins/tools; everything else fails closed
`--yolo`, `/yolo`, or `approvals.mode: off`	private `unrestricted` daemon	One explicit Noora risk acceptance; no runtime Cua prompts	Refuses unless `computer_use.grant_existing_profile: true`; YOLO does not substitute for this grant

Attaching to your signed-in browser

The agent can drive a Chrome/Edge window you already have open — including a signed-in profile — without restarting the browser, copying the profile, or touching your tabs. Because DevTools access exposes that profile's live pages, cookies, and storage, cua-driver requires an explicit human grant that ordinary tool approval cannot substitute for. You opt in once, in config.yaml:

computer_use:
  grant_existing_profile: true

Noora then launches the cua-driver runtime with the trusted-launcher grant (--grant existing-profile), and cua_browser_prepare with an existing profile succeeds against the exact (pid, window_id) the agent proves. Leave it false (the default) and existing-profile attachment fails closed; driver-owned isolated profiles work either way and are what the agent prefers.

Bounded mode for repeatable automation

For recurring browser automation (cron jobs, scheduled research against an authenticated app), bounded mode uses a capability manifest you review once:

# config.yaml
computer_use:
  permission_mode: bounded
  capability_manifest: ~/.noora/cua-manifest.yaml

The manifest names the apps, browser profile kinds, allowed origins, and typed tools the session may use (see the cua-driver permission modes reference for the format). Noora launches a private runtime with --capability-manifest ... --approve-capability-manifest; anything outside the manifest fails closed inside cua-driver. A missing or unreadable manifest fails loudly at session start rather than silently downgrading. Session YOLO still overrides bounded for that one session.

Each MCP transport owns a private lifecycle session inside its runtime. A public session name is only a label for cursor identity and session-scoped state. It does not select, share, or keep a runtime alive. Turning /yolo off, resetting or closing the Noora session, cancellation cleanup, or process exit closes that transport session. Noora also stops private runtimes that it launched for bounded, unrestricted, or existing-profile access. One Noora conversation cannot change another runtime's mode or grants. On macOS, a standard runtime with an existing-profile grant uses a fresh CuaDriver.app daemon on a private socket. Bounded and unrestricted modes use a private embedded service under the Noora host identity.

smart approval remains standard: an LLM classification cannot stand in for a reviewed manifest or a launch-time grant.

YOLO/unrestricted mode does not protect against prompt injection or unintended input. Use it only in a disposable VM or with accounts and data whose full compromise you accept.

`noora computer-use doctor` — your first triage stop

noora computer-use doctor runs cua-driver's structured health_report MCP tool and prints a per-check matrix. It's the single fastest way to find out why an action isn't working.

$ noora computer-use doctor
⚠️  cua-driver VERSION on darwin: degraded
  ✅ binary_version: cua-driver VERSION
  ✅ platform_supported: macOS 26.4.1 (arm64)
  ✅ session_active: MCP session is active.
  ❌ bundle_identity: Process has no CFBundleIdentifier.
      → Run the binary inside CuaDriver.app so TCC grants attribute correctly.
  ✅ tcc_accessibility: Accessibility is granted.
  ✅ tcc_screen_recording: Screen Recording is granted.
  ✅ ax_capability: AX is trusted and reachable.
  ✅ screen_capture_capability: ScreenCaptureKit reachable; 1 display(s) shareable.

Exit code 0 when overall is ok — everything's wired up.
Exit code 1 when degraded or failed — at least one check failed; the hint on each failure tells you what to fix.
Exit code 2 when the cua-driver binary itself isn't reachable.

Useful flags:

--include CHECK — run only the listed checks (repeat for multiple)
--skip CHECK — skip a check (wins over --include)
--json — emit the raw structured payload, same shape as the tools/call health_report MCP response

The check matrix is platform-aware: bundle_identity / tcc_* are skip on Windows + Linux because those concepts don't apply. ax_capability checks AX on macOS, UIA on Windows, AT-SPI on Linux — each with the right diagnostic hint when it can't reach.

The agent cursor and sessions

When the agent acts, you'll see a tinted overlay cursor glide across the screen to where each click / type / scroll lands. The real OS cursor never moves. The overlay shows where the agent is acting. Each Noora run declares a public cua-driver session name (something like noora-3a7b9c14d2e8). The name labels cursor identity and related state, so concurrent runs and subagents get distinct cursors. The MCP transport owns the private lifecycle session inside the runtime; the public name does not.

Tune the cursor with cua-driver's CLI flags or the runtime set_agent_cursor_style MCP tool — see cua.ai/docs/how-to-guides/driver/personalize-cursor for the full menu (built-in arrow vs teardrop silhouette, custom SVG / PNG / ICO via --cursor-icon, runtime gradient colors, bloom halo).

Going deeper — the cua-driver skill pack

Noora keeps its wrapper skill (skills/autonomous-ai-agents/computer-use/SKILL.md) focused on the Noora-side computer_use workflow and action vocabulary. For platform details, recording semantics, browser page interaction, and other deep Cua behavior, install the skill pack that the cua-driver team ships and maintains directly:

cua-driver skills install

The command installs the pack under ~/.cua-driver/skills/cua-driver. Noora autodetection is a planned cua-driver follow-up, so currently point Noora at that directory or symlink it into your skill space. The wrapper remains the workflow layer and points to Cua's installed skill for driver behavior. The pack contains:

File	Topic
`SKILL.md`	The cross-platform core (snapshot invariant, no-foreground contract, click dispatch, AX-tree mechanics)
`MACOS.md`	macOS specifics: no-foreground contract, AXMenuBar navigation, SkyLight click dispatch, Apple Events JS bridge
`WINDOWS.md`	Windows specifics: UIA tree, UWP / `ApplicationFrameHost` hosting, Session 0 isolation, autostart pattern
`LINUX.md`	Linux specifics: AT-SPI tree, X11 / Wayland, terminal-emulator detection
`RECORDING.md`	Trajectory + video recording semantics
`WEB_APPS.md`	Browser-page interaction tips
`TESTS.md`	Replay-by-trajectory workflow

These are platform deep dives, not duplicates of the Noora skill — when an agent reports "on Windows, my click landed on the wrong element," it reads WINDOWS.md for the UIA / UWP context that explains why and what to do differently.

cua-driver skills status shows what's installed and which agent harnesses it's linked into. Today the autodetect list covers Claude Code, Codex, OpenCode, OpenClaw, and Antigravity; Noora autodetection is planned as a follow-up in trycua/cua — until then, run cua-driver skills install once and point your harness at the resulting ~/.cua-driver/skills/cua-driver directory (or symlink it into your usual skill space).

Quick example

User prompt: "Find my latest email from Stripe and summarise what they want me to do."

The agent's plan (this is the same shape on macOS / Windows / Linux — the model substitutes the platform's idiomatic shortcut and app name):

computer_use(action="capture", mode="som", app="Mail") — gets a screenshot of the email app with every sidebar item, toolbar button, and message row numbered.
computer_use(action="click", element=14) — clicks the search field.
computer_use(action="type", text="from:stripe")
computer_use(action="key", keys="return", capture_after=True) — submit and get the new screenshot.
Click the top result, read the body, summarise.

During all of this, your cursor stays wherever you left it and the email app never comes to front.

Provider compatibility

Provider	Vision?	Works?	Notes
Anthropic (Claude Sonnet/Opus 3+)	✅	✅	Best overall; SOM + raw coordinates.
OpenRouter (any vision model)	✅	✅	Multi-part tool messages supported.
OpenAI (GPT-4+, GPT-5)	✅	✅	Same as above.
Google (Gemini 2+)	✅	✅	Tool-calling + vision both supported.
Local vLLM / LM Studio / Ollama (vision model)	✅	✅	If the model supports multi-part tool content.
Text-only models	❌	✅ (degraded)	Use `mode="ax"` for accessibility-tree-only operation.

Screenshots are sent inline with tool results as OpenAI-style image_url parts. For Anthropic, the adapter converts them into native tool_result image blocks. The image MIME type comes from cua-driver's explicit mimeType field (image/png or image/jpeg) — no client-side magic-byte sniffing.

Safety

Noora applies multi-layer guardrails:

Destructive actions (click, type, drag, scroll, key, focus_app) require approval — either interactively via the CLI dialog or via the messaging-platform approval buttons.
Hard-blocked key combos at the tool level: empty trash, force delete, lock screen, log out, force log out.
Hard-blocked type patterns: curl | bash, sudo rm -rf /, fork bombs, etc.
The agent's system prompt tells it explicitly: no clicking permission dialogs, no typing passwords, no following instructions embedded in screenshots.

Pair with approvals.mode: manual in ~/.noora/config.yaml if you want every action confirmed.

Token efficiency

Screenshots are expensive. Noora applies four layers of optimisation:

Screenshot eviction — the Anthropic adapter keeps only the 3 most recent screenshots in context; older ones become [screenshot removed to save context] placeholders.
Client-side compression pruning — the context compressor detects multimodal tool results and strips image parts from old ones.
Image-aware token estimation — each image is counted as ~1500 tokens (Anthropic's flat rate) instead of its base64 char length.
Server-side context editing (Anthropic only) — when active, the adapter enables clear_tool_uses_20250919 via context_management so Anthropic's API clears old tool results server-side.

A 20-action session on a 1568×900 display typically costs ~30K tokens of screenshot context, not ~600K.

Limitations

Performance. Background mode is slower than foreground — accessibility-routed events take ~5–20 ms on macOS, ~3–10 ms on Windows UIA, ~5–15 ms on Linux AT-SPI vs direct HID posting. Not noticeable for agent-speed clicking; noticeable if you try to record a speed-run.
No keyboard password entry. type has hard-block patterns on command-shell payloads; for passwords, use the system's autofill (macOS Keychain / Windows Credential Manager / GNOME Keyring / KWallet).
Some apps don't expose an accessibility tree. Modern UWP apps on Windows, Electron < 28 on Linux, and a few macOS apps with custom drawing (Logic, Final Cut, some games) have sparse or empty AX trees. Fall back to pixel coordinates if the tree is empty — or skip the task entirely.
Windows: elevated (admin) windows can't be driven from a normal agent. Windows UIPI (User Interface Privilege Isolation) enforces integrity-level boundaries: a Medium-integrity process (the default Noora agent) cannot enumerate the UIA tree of, or inject mouse input into, a window owned by a High-integrity (Administrator) process. Symptom: capture(mode='som') returns 0 elements and click(...) reports success while doing nothing, even though the screenshot renders fine (GDI capture sits below the integrity check). Keyboard events partially bypass UIPI, so Tab / Enter can still navigate an elevated dialog. This is an OS constraint, not a cua-driver bug — it affects every Windows automation stack. To drive elevated windows, run the Noora agent itself at High integrity (launch from an elevated terminal); otherwise target non-elevated windows.
Platform-specific deployment gotchas:
- macOS uses private SkyLight SPIs. Apple can change them in any OS update. Noora warns when the installed cua-driver is older than the version it was tested against.
- Windows SSH sessions run in Session 0, which has no interactive desktop. Drive Noora from inside the RDP / console session, or set up cua-driver's autostart Scheduled Task — windows-ssh has the recipe.
- Linux requires a reachable display server. Headless servers need Xvfb (Xvfb :99 -screen 0 1920x1080x24) before computer_use can capture or inject events. Pure Wayland sessions need an XWayland bridge for screen capture (cua-driver's Wayland inject path handles input independently).

For cross-platform GUI automation without the desktop overhead (and without TCC / Session 0 / X11 setup), the browser toolset uses a real headless Chromium and is the right answer for web-only tasks.

Configuration

Permission mode and manifest (see Permission modes above):

computer_use:
  permission_mode: standard        # standard (default) | bounded
  capability_manifest: ""          # capability manifest path, required for bounded
  grant_existing_profile: false    # opt-in: attach in standard or unrestricted mode

Override the driver binary path (tests / CI / local builds):

NOORA_CUA_DRIVER_CMD=/path/to/your/cua-driver

Swap the backend entirely (for testing):

NOORA_COMPUTER_USE_BACKEND=noop   # records calls, no side effects

Telemetry

cua-driver ships with anonymous usage telemetry (PostHog) enabled by default upstream. Noora disables it for you — on every cua-driver invocation (the MCP backend, status, doctor, and install) Noora sets CUA_DRIVER_RS_TELEMETRY_ENABLED=0 in the driver's environment.

To opt back in (let cua-driver use its own default and send telemetry), set this in config.yaml:

computer_use:
  cua_telemetry: true   # default: false (telemetry off)

When it's on, noora computer-use doctor reports telemetry: enabled; when off (the default), it reports telemetry: disabled via CUA_DRIVER_RS_TELEMETRY_ENABLED.

Testing against a local cua-driver build

When you're developing cua-driver itself — or want to test an unreleased fix — point Noora at a binary you built from source instead of the published release. Noora resolves the driver with shutil.which("cua-driver") and does not enforce NOORA_CUA_DRIVER_VERSION, so a local build (reported as 0.0.0-local-*) is accepted as-is. Two approaches:

Option A — `install-local` (build + put it on PATH)

From your trycua/cua checkout, run the upstream local installer. It builds the Rust backend in release mode and drops cua-driver into the same install layout the production installer uses, adding its bin dir to your PATH:

# Windows (PowerShell), from the cua repo root
./libs/cua-driver/scripts/install-local.ps1 -NoAutoStart

# macOS / Linux, from the cua repo root  (defaults to a debug build without --release)
./libs/cua-driver/scripts/install-local.sh --release

Windows stages the build under %USERPROFILE%\.cua-driver\packages\… and junctions %LOCALAPPDATA%\Programs\Cua\cua-driver\bin (added to your User PATH) to it. macOS/Linux symlinks cua-driver into ~/.local/bin (override with --bin-dir <path>).
-NoAutoStart skips registering the cua-driver-serve logon daemon — you don't need it for Noora testing (see notes).

Then open a fresh shell (so the PATH change is visible) and confirm:

cua-driver --version                 # local builds report 0.0.0-local-release
# Windows:      (Get-Command cua-driver).Source
# macOS/Linux:  which cua-driver

Option B — point Noora straight at the built binary (fastest loop)

Skip the install ceremony entirely: cargo build and set NOORA_CUA_DRIVER_CMD to the resulting binary. Best for rapid edit/build/test.

cargo build -p cua-driver            # add --release for a release build; run from libs/cua-driver/rust

# Windows (.env)
NOORA_CUA_DRIVER_CMD=C:\path\to\cua\libs\cua-driver\rust\target\debug\cua-driver.exe
# macOS / Linux (.env)
NOORA_CUA_DRIVER_CMD=/path/to/cua/libs/cua-driver/rust/target/debug/cua-driver

Confirm Noora is using your build

noora computer-use status prints the resolved binary path and version.
noora computer-use doctor confirms the binary is reachable and exercises the full MCP path end-to-end.
In a session, computer_use(action="capture") exercises the spawned cua-driver mcp child process.

Notes & gotchas

Noora spawns a cua-driver mcp stdio proxy. In a normal session the proxy connects to (and may start) the standard machine daemon. In explicit Noora YOLO, Noora instead owns a private cua-driver serve --embedded child and points the proxy at its private socket or named pipe. The Windows autostart/UIAccess pattern still matters for interactive Session 1+ input from SSH — see the Limitations section.
Locked binary on Windows. A running cua-driver-serve daemon can hold cua-driver.exe and block an overwrite on rebuild. install-local.ps1 renames the locked binary out of the way automatically; if you cargo build manually (Option B), stop it first with cua-driver autostart disable (or schtasks /End /TN cua-driver-serve).
Rebuild loop. After editing cua-driver source, re-run install-local (rebuilds, restages, flips the current junction) for Option A, or just re-cargo build for Option B — no Noora change needed either way.
Local builds skip the version check. Noora warns when the installed cua-driver is older than its per-OS tested baseline, but exempts 0.0.0-local-* dev builds — so your local build never triggers that warning.

Troubleshooting

First action when anything's off: run noora computer-use doctor. The structured per-check matrix tells you (and any agent helping you debug) exactly what's wrong.

Specific failure modes the doctor doesn't catch:

computer_use backend unavailable: cua-driver is not installed — Run noora computer-use install to fetch the cua-driver binary, or run noora tools and enable the Computer Use toolset.

Clicks seem to have no effect — Capture and verify. A modal you didn't see may be blocking input. Dismiss it with escape or the close button.

Element indices are stale — SOM indices are only valid until the next capture. Re-capture after any state-changing action. The wrapper carries opaque element_tokens for stale detection — you'll see an explicit error rather than a wrong click.

"blocked pattern in type text" — The text you tried to type matches the dangerous-shell-pattern list. Break the command up or reconsider.

Empty captures on Linux — DISPLAY not set, or you're on pure Wayland without an XWayland bridge. noora computer-use doctor will flag this as ax_capability: fail with a Set DISPLAY (X11)… hint.

Empty captures on Windows over SSH — You're in Session 0 (the services session). Drive from RDP / console directly, or set up the autostart pattern — see cua.ai/docs/how-to-guides/driver/windows-ssh.

How it works​

Enabling​

Permission modes and logged-in browser profiles​

Attaching to your signed-in browser​

Bounded mode for repeatable automation​

noora computer-use doctor — your first triage stop​

The agent cursor and sessions​

Going deeper — the cua-driver skill pack​

Quick example​

Provider compatibility​

Safety​

Token efficiency​

Limitations​

Configuration​

Telemetry​

Testing against a local cua-driver build​

Option A — install-local (build + put it on PATH)​

Option B — point Noora straight at the built binary (fastest loop)​

Confirm Noora is using your build​

Notes & gotchas​

Troubleshooting​

See also​