Clicky AI desktop assistant
Talk to your screen and it actually listens. The desktop AI for non-technical operators tired of switching between five apps to finish one task.
Who this is for
Best for non-technical founders, operations leads, and teams that hate switching between five apps to finish one task.
We would package a business-ready Clicky setup: approved data scopes, a custom voice persona, a sales-call mode, and shortcut presets for the team.
Setup steps
Download the latest Clicky release or build from source following the repository instructions.
Grant the required screen and accessibility permissions on macOS or Windows.
Test it on a low-stakes workflow before connecting work documents or client data.
Decide which apps and screens it is allowed to see, and write that policy down.
Before you connect live data
- • Run dummy data first. Real client data is not a test bed.
- • API keys never go in a public repo. Use env vars and a secrets manager.
- • Add logging, access control, monitoring, and a rollback path before launch.
- • Read the license. Forking a repo without checking is how lawsuits start.
Credit the original author
Check the current repository license and any per-platform terms before deploying inside a client environment.
We list this as a guide, not as our build, unless we are actively maintaining a fork.
Paste this into Claude. It will install it for you.
Open Claude or Claude Code. Paste the prompt below. It will ask you a few setup questions, then walk you through every step adapted to your machine.
You are helping me install and run **Clicky AI desktop assistant** on my machine. Repo / link: https://github.com/openclicky/openclicky Category: Desktop AI What it does: Talk to your screen and it actually listens. The desktop AI for non-technical operators tired of switching between five apps to finish one task. Difficulty: Easy Setup steps from the public guide: 1. Download the latest Clicky release or build from source following the repository instructions. 2. Grant the required screen and accessibility permissions on macOS or Windows. 3. Test it on a low-stakes workflow before connecting work documents or client data. 4. Decide which apps and screens it is allowed to see, and write that policy down. Before writing or running anything, ask me these in ONE batch and wait for my reply: 1. What operating system am I on? (macOS / Windows / Linux) 2. Do I already have Docker installed and running? 3. Do I have Git installed? 4. Do I have Node or Python installed, and what versions? 5. Which model provider keys do I have available right now? (Anthropic, OpenAI, Gemini, OpenRouter, none) 6. Where do I want this installed on disk? 7. Is this just to test locally, or am I planning to connect it to live business data soon? 8. Anything sensitive (real client data, payment access, mailbox access) it should NOT touch on this machine? After I answer, walk me through each setup step adapted to my environment. Stop after each step, show me the command, and wait for me to confirm it ran before moving on. If a step fails, diagnose the actual error before suggesting the next move. Do not connect this to live business data until I explicitly say go.
Want it wired into your business instead of your laptop?
A repo on your machine is a starting point. The work that pays back is connecting it to the CRM, inbox, payments, and team processes you already run. That is the part we ship.