Hi, this is Clicky.

It's an AI buddy that lives next to your cursor. It can see your screen, talk to you, and even point at stuff. Kinda like having a real teacher next to you.

Download it here for free.

Here's the original tweet that kinda blew up for a demo for more context.

This is the open-source version of Clicky for those that want to hack on it, build their own features, or just see how it works under the hood.

Platforms

Platform	Status	Details
Windows	Shipping	Uses local Codex/ChatGPT sign-in for the LLM, plus bring-your-own speech keys. See windows/README.md
macOS	Shipping	Uses a Cloudflare Worker proxy for API keys. See setup below

Windows — quick start

1. Install the Codex CLI and sign in with ChatGPT/Codex.
2. Enter your AssemblyAI and ElevenLabs keys in Clicky Settings.
3. Hold Ctrl+Alt and talk.

Speech keys are encrypted with Windows DPAPI and never leave your machine. Clicky's Windows LLM path talks to the local codex app-server, so it can use your Codex/ChatGPT sign-in instead of an OpenAI API key. See windows/README.md for full details, local development, and system requirements.

To run locally from source:

.\run.cmd

macOS — quick start

The fastest way to get this running is with Claude Code.

Once you get Claude running, paste this:

Hi Claude.

Clone https://github.com/farzaa/clicky.git into my current directory.

Then read the CLAUDE.md. I want to get Clicky running locally on my Mac.

Help me set up everything — the Cloudflare Worker with my own API keys, the proxy URLs, and getting it building in Xcode. Walk me through it.

That's it. It'll clone the repo, read the docs, and walk you through the whole setup. Once you're running you can just keep talking to it — build features, fix bugs, whatever. Go crazy.

Manual macOS setup

If you want to do it yourself, here's the deal.

Prerequisites

• macOS 14.2+ (for ScreenCaptureKit)
• Xcode 15+
• Node.js 18+ (for the Cloudflare Worker)
• A Cloudflare account (free tier works)
• API keys for: Anthropic, AssemblyAI, ElevenLabs

1. Set up the Cloudflare Worker

The Worker is a tiny proxy that holds your API keys. The Mac app talks to the Worker, the Worker talks to the APIs. This way your keys never ship in the app binary.

cd worker
npm install

Now add your secrets. Wrangler will prompt you to paste each one:

npx wrangler secret put ANTHROPIC_API_KEY
npx wrangler secret put ASSEMBLYAI_API_KEY
npx wrangler secret put ELEVENLABS_API_KEY

For the ElevenLabs voice ID, open wrangler.toml and set it there (it's not sensitive):

[vars]
ELEVENLABS_VOICE_ID = "your-voice-id-here"

Deploy it:

npx wrangler deploy

It'll give you a URL like https://your-worker-name.your-subdomain.workers.dev. Copy that.

2. Run the Worker locally (for development)

If you want to test changes to the Worker without deploying:

cd worker
npx wrangler dev

This starts a local server (usually http://localhost:8787) that behaves exactly like the deployed Worker. You'll need to create a .dev.vars file in the worker/ directory with your keys:

ANTHROPIC_API_KEY=sk-ant-...
ASSEMBLYAI_API_KEY=...
ELEVENLABS_API_KEY=...
ELEVENLABS_VOICE_ID=...

Then update the proxy URLs in the Swift code to point to http://localhost:8787 instead of the deployed Worker URL while developing. Grep for clicky-proxy to find them all.

3. Update the proxy URLs in the app

The app has the Worker URL hardcoded in a few places. Search for your-worker-name.your-subdomain.workers.dev and replace it with your Worker URL:

grep -r "clicky-proxy" leanring-buddy/

You'll find it in:

• CompanionManager.swift — Claude chat + ElevenLabs TTS
• AssemblyAIStreamingTranscriptionProvider.swift — AssemblyAI token endpoint

4. Open in Xcode and run

open leanring-buddy.xcodeproj

In Xcode:

1. Select the leanring-buddy scheme (yes, the typo is intentional, long story)
2. Set your signing team under Signing & Capabilities
3. Hit Cmd + R to build and run

The app will appear in your menu bar (not the dock). Click the icon to open the panel, grant the permissions it asks for, and you're good.

Permissions the app needs

• Microphone — for push-to-talk voice capture
• Accessibility — for the global keyboard shortcut (Control + Option)
• Screen Recording — for taking screenshots when you use the hotkey
• Screen Content — for ScreenCaptureKit access

Architecture

If you want the full technical breakdown, read CLAUDE.md. But here's the short version:

Menu bar / system tray app with a control panel and a full-screen transparent cursor overlay. Push-to-talk streams audio to AssemblyAI for real-time transcription, sends the transcript + screenshots to an LLM via local Codex app-server on Windows or the Mac proxy path on macOS, and plays the response through ElevenLabs TTS. The LLM can embed [POINT:x,y:label:screenN] tags in its responses to make the blue cursor fly to specific UI elements across multiple monitors.

• Mac: APIs proxied through a Cloudflare Worker (worker/)
• Windows: Local Codex app-server for the LLM, direct AssemblyAI/ElevenLabs clients with encrypted local key storage (no worker needed)

Project structure

leanring-buddy/          # Swift source (macOS, yes the typo stays)
windows/                 # C# / .NET 8 / WPF (Windows)
worker/                  # Cloudflare Worker proxy (used by Mac only)
CLAUDE.md                # Full architecture doc (agents read this)

Contributing

PRs welcome. If you're using Claude Code, it already knows the codebase — just tell it what you want to build and point it at CLAUDE.md.

Got feedback? DM me on X @farzatv.