awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
farzaa avatar

farzaa/clicky

0
View on GitHub↗
www.heyclicky.com↗

Clicky

Clicky is a macOS menu bar app that acts as an AI screen companion. It captures a screenshot of what the user is looking at, listens to a spoken question, and answers aloud while a transparent cursor overlay points at the relevant interface element. It runs with no dock icon or main window, opening a floating control panel from the status bar.

Voice interaction is built around a global push-to-talk shortcut that works from any app. Speech is transcribed live through interchangeable providers, including on-device recognition, a streaming service, and an audio transcription service. Each question sends the transcript together with a fresh screenshot to a language model. Replies stream back piece by piece and are turned into synthesized speech, so spoken answers can begin before the full text is complete. When a reply includes position tags, the overlay cursor moves to the matching element, including across multiple monitors.

All outside service calls for language model, transcription, and speech go through a small Cloudflare Worker that holds the secret keys, so no credentials ship inside the installed app.

The repository also covers distribution. A single script builds, signs, notarizes, and packages the app as a disk image, publishes a GitHub release, and generates a signed update feed that installed copies use to find and download new versions.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • AI Chat Assistants - Provide an on-screen AI teacher beside the cursor that sees the screen, answers by voice, and helps users learn while they work.
  • On-Screen Content Question Answerers - Answers spoken questions by capturing the current screen and sending it with the transcript to a language model, then pointing at the relevant element.
  • Voice-to-Voice Loops - Captures push-to-talk speech, transcribes it live, sends it with a screenshot to a language model, and speaks the reply back.
  • Screen-Aware Prompt Contexts - Each question bundles a fresh screen capture with the spoken transcript, letting the model answer from exactly what the user currently sees.
  • Screenshot Question Answering - Send a captured screenshot together with the spoken transcript to a language model and stream its reply back a piece at a time.
  • AI Desktop Assistants - Provides a desktop AI helper that users talk to by voice and that answers aloud while they work on their computer.
  • Contextual Help Systems - Answers questions about whatever is on the user's display using a fresh screenshot and points at the exact interface element needed.
  • Screen Capture and Text Extraction - Capture screenshots of the current display so an assistant can understand the user's context and answer questions about what is visible.
  • Push-to-Talk Voice Dictation Shortcuts - Uses a system-wide keyboard shortcut to record speech from any app, stream live transcription, and play back synthesized spoken replies.
  • API Key Proxying - Routes every language model, transcription, and speech request through a cloud proxy that holds the secret keys, so no credentials ship in the app.
  • Menu Bar Utilities - Ships as a lightweight menu bar app with a dropdown panel, global shortcut, and a transparent full-screen overlay.
  • Interface Element Highlighting - Moves a transparent cursor overlay onto the interface element named in a reply, across multiple monitors, to guide the user's attention.
  • Multimodal Response Pipelines - Language model replies arrive piece by piece and feed straight into speech synthesis, so spoken answers begin before the full text is finished.
  • Speech Transcription - Transcribes spoken questions live through interchangeable providers, including on-device recognition, a streaming service, and an audio transcription service.
  • Spoken Reply Playback - Streams the model's answer as it is generated and speaks it aloud so users can listen instead of read.
  • Software Update Feeds - Signs the installer with an update key and generates a versioned feed file that installed copies use to find and download new releases.
  • Screen Capture Utilities - Capture the visible screen and pair it with a spoken question so an assistant can answer using exactly what the user is looking at.
  • Mac App Release Pipelines - Runs one script that builds, signs, notarizes, packages as a disk image, publishes a release, and generates the update feed.
  • Cloud Speech Synthesizers - Converts streamed assistant replies into natural-sounding speech through a cloud text-to-speech service and plays it back as the reply arrives.
  • Update Feed Distributors - A single script builds, signs, notarizes, and packages the app, then publishes a versioned feed file that installed copies poll to find and download updates.
  • Cloudflare Worker Proxies - Ships a serverless Cloudflare Worker that stores secret keys and forwards chat, transcription, and speech requests from the app.
  • Secure API Proxies - A small cloud worker holds all secret keys and forwards every outside service request, so no sensitive credentials ever ship inside the installed app.
  • Screen Element Pointers - The model embeds position tags in its replies, and a transparent overlay cursor parses them and glides to the matching element across multiple monitors.
  • Global Shortcut Listeners - Listens for a system-wide push-to-talk keyboard shortcut that starts and stops microphone capture from any app.
  • Menu Bars - Runs entirely from the system status bar with no dock icon or main window, opening a floating voice control panel on click.
7,957 stars·1,595 forks·Swift·MIT·6 views

Star history

Star history chart for farzaa/clickyStar history chart for farzaa/clicky

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does farzaa/clicky do?

Clicky is a macOS menu bar app that acts as an AI screen companion. It captures a screenshot of what the user is looking at, listens to a spoken question, and answers aloud while a transparent cursor overlay points at the relevant interface element. It runs with no dock icon or main window, opening a floating control panel from the status bar.

What are the main features of farzaa/clicky?

The main features of farzaa/clicky are: AI Chat Assistants, On-Screen Content Question Answerers, Voice-to-Voice Loops, Screen-Aware Prompt Contexts, Screenshot Question Answering, AI Desktop Assistants, Contextual Help Systems, Screen Capture and Text Extraction.

Which projects share features with farzaa/clicky?

Projects with overlapping indexed features include: vorssaint/vorssaint-utils — Vorssaint Utils is a free, open-source collection of system utilities for macOS that lives in the menu bar. It bundles… sylinko/everywhere — Everywhere is a desktop AI assistant that understands whatever is on your screen and can act across applications… aardio/imtip — ImTip is a desktop utility that provides input method visualization and large language model integration. It renders… mg-chao/snow-shot — This project is an AI-powered screenshot manager and visual assistant designed for capturing screen content and… duongductrong/snapzy — Snapzy is a native macOS menu bar app for taking screenshots and recording the screen. Screenshots cover the full… shadowsocksr-backup/shadowsocks-rss — Shadowsocks-rss is an RSS feed generator and version tracker designed to automate the distribution of update…

Projects sharing features with Clicky

These projects share indexed features with Clicky. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • vorssaint/vorssaint-utilsvorssaint avatar

    vorssaint/vorssaint-utils

    33,404View on GitHub↗

    Vorssaint Utils is a free, open-source collection of system utilities for macOS that lives in the menu bar. It bundles tools for audio, window management, clipboard handling, input devices, screen capture, and system monitoring into a single app. Audio control covers separate volume levels for each app, boosts above 100 percent, routing apps to different outputs without an audio driver, and microphone selection and muting by shortcut. Window management includes snapping and tiling into saved layouts, app and window switching with previews, Dock hover previews, and protection against accidenta

    Swiftalt-tabapp-uninstallerappkit
    View on GitHub↗33,404
  • sylinko/everywhereSylinko avatar

    Sylinko/Everywhere

    6,093View on GitHub↗

    Everywhere is a desktop AI assistant that understands whatever is on your screen and can act across applications without requiring screenshots or manual context switching. It reads structured UI data through accessibility and automation APIs to perceive the active application and visible content, then provides context-aware help, summaries, translations, and answers to natural language questions about what you are viewing. The tool distinguishes itself by combining on-screen content analysis with a multi-LLM agent platform that routes requests to providers like OpenAI, Anthropic, and local mo

    C#aiai-agentsai-assistant
    View on GitHub↗6,093
  • mg-chao/snow-shotmg-chao avatar

    mg-chao/snow-shot

    4,118View on GitHub↗

    This project is an AI-powered screenshot manager and visual assistant designed for capturing screen content and processing it through large language models. It functions as an OCR translation application and screen annotation tool, allowing users to extract text from images and perform intelligent analysis of visual data. The software differentiates itself through an AI-driven OCR pipeline and the ability to convert screenshots into structured Markdown or HTML via layout-aware document transformation. It features a visual AI assistant capable of analyzing screen content and a prompt-engineere

    TypeScriptchatbotocrscreen-capture
    View on GitHub↗4,118
  • aardio/imtipaardio avatar

    aardio/ImTip

    2,580View on GitHub↗

    ImTip is a desktop utility that provides input method visualization and large language model integration. It renders real-time indicators at the system text cursor to track language, layout, and punctuation settings. The project connects large language model APIs to a desktop interface to render rich content, including mathematical formulas and syntax-highlighted code. It uses a scriptable logic engine and global hooks to map programmable hotkeys to complex task sequences and external API calls. The software includes tools for desktop UI customization, allowing users to adjust the style, col

    aardioimeinput-method
    View on GitHub↗2,580
Compare all 30 related projects→