LocalClicky
UnclaimedControl your Mac with voice commands, entirely offline and privacy-focused.
Visit WebsiteFreemiumVisit Website
Tracked since2026
0 reviews trackedThe Bottom Line
Entry price
Free plan available, paid tiers above
Biggest pro
Ensures maximum privacy as no data leaves the user's machine
Biggest con
Requires manual setup and installation of dependencies like Whisper.cpp and Ollama
TL;DR - LocalClicky
- Offline voice control for macOS using local AI models.
- Enhances privacy by keeping all data and processing on your machine.
- Performs various tasks including app control, cursor movement, and shell commands.
Pricing: Free plan available
Best for: Growing teams
What is LocalClicky?
LocalClicky is an open-source macOS voice assistant that allows users to control their computer using natural language commands, without relying on cloud services or external APIs. It performs tasks like opening applications, adjusting system settings, controlling media playback, managing files, and interacting with on-screen elements by moving the cursor and clicking. The tool prioritizes user privacy by processing all voice commands, screen captures, and AI reasoning locally on the user's machine.
Designed for users who value privacy and offline functionality, LocalClicky integrates local AI models for transcription, reasoning, and vision. It operates from the menubar, remaining unobtrusive until activated by a wake word. Its capabilities include understanding context, performing multi-round tool calls, and maintaining conversation memory within a session, making it a powerful and secure alternative to cloud-based voice assistants for macOS users.
Pros & Cons
Pros
- Ensures maximum privacy as no data leaves the user's machine
- Operates entirely offline, ideal for environments without internet access or for sensitive tasks
- Offers robust control over macOS functionalities through natural language
- Free and open-source, allowing for transparency and community contributions
Cons
- Requires manual setup and installation of dependencies like Whisper.cpp and Ollama
- Performance is dependent on local hardware capabilities
- Currently limited to macOS, not available on other operating systems
Key Features
Completely offline operationNo cloud APIs, API keys, or subscriptions requiredMenubar integration without Dock iconWake word activation (e.g., "Computer")Voice Activity Detection for automatic recording stopOn-demand screen vision using local AI modelsCursor movement and clicking based on screen contentControl macOS applications (open, quit, adjust volume)
Pricing Plans
Free TrialFree
$0 USD per month
- Unlimited public/private repositories
- Dependabot security and version updates
- 2,000 CI/CD minutes/month (Free for public repositories)
- 500MB of Packages storage (Free for public repositories)
- Issues & Projects
- Community support
Team
$4 USD per user/month
- Everything included in Free
- Access to GitHub Codespaces
- Repository rules
- Multiple reviewers in pull requests
- Draft pull requests
- Code owners
- Required reviewers
- Pages and Wikis
Enterprise
Starting at $21 USD per user/month
- Everything included in Team
- Data residency
- Enterprise Managed Users
- User provisioning through SCIM
- Enterprise Account to centrally manage multiple organizations
- Environment protection rules
- Repository rules
- Audit Log API
Reviews
$99Free with your review
Write a reviewReview LocalClicky, get a free AI guide
Share your experience and we will send you Improve Your Thinking Patterns Using ChatGPT, free.
Explore More
LocalClicky FAQ
What specific AI models does LocalClicky use for its local processing?
LocalClicky utilizes Whisper.cpp for transcription, and Ollama (specifically qwen3 for command modeling and gemma4 for vision) for AI reasoning and screen analysis. Text-to-speech is handled by macOS's built-in 'say' command.
How does LocalClicky ensure user privacy without sending data to the cloud?
LocalClicky processes all user input, including voice recordings, screen captures, and commands, directly on the user's macOS machine using locally installed AI models. No data is transmitted to external servers or cloud APIs.
What macOS permissions are required for LocalClicky to function, and why?
LocalClicky requires Microphone access for voice recording, Screen Recording for the vision model to analyze the screen, and Accessibility access for controlling the cursor and performing clicks. These permissions are necessary for its core functionalities.
Can LocalClicky interact with specific elements on my screen, such as buttons or icons?
Yes, LocalClicky can interact with on-screen elements. It uses a local vision model to take screenshots on demand, identify elements like notification bells or buttons, and then moves the cursor and clicks them based on your voice commands.
How does LocalClicky handle continuous conversation or a series of related commands?
LocalClicky features a 'session mode' where it stays active after an initial command, allowing you to chain subsequent commands without repeating the wake word. It also maintains conversation memory for the last 10 exchanges within a session.
What happens if I stop talking during a recording session?
LocalClicky employs Voice Activity Detection (VAD) to automatically stop recording when you cease speaking. If VAD is not installed, it defaults to a 30-second hard cap for recording duration.
Source: github.com