Manual
Fire it yourself
Global hotkeys and a command palette. The work you want to stay in control of, one keystroke away.
run flow…
- Invoice triage⌥⌘I
- Weekly recap⌘⇧R
- Clipboard → task⌥⌘T
- Screenshot to notes⌥⌘S
Desktop automation with AI
Build automations and agents on your desktop.
Describe what you need and AI builds the workflow on your machine. Run it with a hotkey, on a schedule, or hand it to an agent that decides for itself.
01 · Plan first
You review the plan before anything runs.
Every request becomes a written plan with the steps, the code it intends to generate, and the services it will touch. Approve it and the flow gets built.
You pull the trigger: hotkey, palette, or a pinned button.
Your plan
weekly-recap.plan01
Phase 01·Kick off
trigger.manual
You decide when it runs. No schedule, no webhook, just you
01aHotkey
hotkey.modifier+I
Press ⌘⇧I from anywhere in the desktop app
01bCommand palette
palette.run_flow
Search your flows and hit Enter to launch
01cToolbar pin
ui.button.run
One click on a pinned action in the toolbar
02
Phase 02·Confirm
prompt.confirm
Quick prompt for week range or recipient before it runs
03
Phase 03·Run
pipeline.execute
Snapshot metrics, format the recap, and stage the output
04
Phase 04·Deliver
action.copy_and_notify
Copy to clipboard and drop a Slack summary when done
The flow
7 nodes · 6 edgescompiled.flowready · manual
Automated
Let schedules run it
Cron and event triggers keep the routine firing while you're away from the keyboard.
next run · weekdays 09:00
Agentic
Hand it to an agent
Agents watch the run, pick tools, spawn subagents, and prepare the report you actually read.
warnings · 3
errors · 2
03 · The build fabric
invoice-tracker.flow · 5 nodes
04 · Outputs
Every run leaves something you can read.
Flows write their results as pins — markdown, stats, tables, and timelines. The Gallery in the desktop app shows the latest run per flow so you can read what happened without digging through logs.
3 / 3 flows · Gallery output
Invoice follow-up
New invoice email parsed. Amount and due date logged. Team notified if overdue.
invoice-triage · live · Gmail · new email
| Client | Status |
|---|---|
| Acme Studio | Paid |
| Beta Works | Overdue |
| Northline | Sent |
New invoice email parsed. Amount and due date logged. Team notified for Beta Works.
Today
Logged & notified
Wed
Reminder email
Fri
Escalate if needed
Same pin layouts as the desktop app Gallery: markdown, stat cards, tables, and timelines — one readable surface per flow run.
Pricing
Pay for the app, not per automation run.
Runs happen on your hardware, so there is no per-execution meter. You bring your own model keys and pay providers directly.
Free
$0
For trying the desktop app and building your first few flows.
- Unlimited local flow runs
- Hotkey and manual triggers
- Bring your own model keys
- Up to 3 saved flows
Pro
Popular$19/month
For people who live in their automations every day.
- Unlimited saved flows
- Schedule and event triggers
- Agent Studio with subagents
- Skills library and connectors
- Priority build model routing
Team
$49/user/month
For teams sharing flows, agents, and connector setups.
- Everything in Pro
- Shared flow and agent library
- Connector config sharing
- Audit log of local runs
- Priority support
Model usage is billed by your provider. Cancel any time — your flows stay on disk and keep running.
FAQ
Questions worth asking.
Do I need to know how to code?
No. You describe the automation in plain language and the app drafts a plan, then builds it. The output happens to be TypeScript, so if you do read code you can open any step and change it.
Where do my API keys live?
In your operating system keychain. They are read at run time on your machine and sent only to the provider you configured. They never pass through our servers, because there are no servers in the run path.
What happens if I cancel?
The app keeps working for local and manual runs, and your flows stay on disk as files you own. You lose access to paid features like schedules and Agent Studio.
Can it reach my internal tools?
Yes, and that is the point of running locally. Flows execute inside your network, so anything your machine can reach — an intranet API, a VPN service, a local database — is reachable without opening it to the internet.
Which models can I use?
Any provider you hold a key for, plus local models through LM Studio. You can route the planning step and the run steps to different models to control cost.
How is this different from Zapier or n8n?
Those run your workflow on their infrastructure and charge per task. This is a desktop app: the AI writes real code steps, execution happens on your hardware, and there is no per-run meter.
Start building with AutomationGhost today.
Free to download, no account required. Describe the first automation and let it build itself.
v0.9 · 84 MB · Apple silicon and Intel