Blueturboguy07/cue

Open-source macOS AI copilot that floats over your screen, sees/hears your meetings, and stays hidden from screen shares. Cluely alternative, bring-your-own-key.

What it solves

cue is an AI copilot designed for live meetings and coding problems. It provides real-time assistance by monitoring your screen and audio, while remaining invisible to screen-sharing software so it can act as a private assistant during calls.

How it works

The application is an Electron-based overlay that captures three distinct inputs: your screen (via screenshots), your microphone, and the system's meeting audio (the other participants). These inputs are transcribed using either cloud providers (OpenAI, Gemini, Deepgram) or a local whisper.cpp runtime. The resulting text and visual data are then sent to a chosen LLM (OpenAI, Anthropic, Gemini, etc.) to generate responses that stream directly into a transparent, always-on-top glass panel.

Who it’s for

It is intended for professionals and students who need real-time, discreet assistance during live conversations, coding sessions, or study practice.

Highlights

  • Screen-share invisibility: Uses OS-level flags (WDA_EXCLUDEFROMCAPTURE on Windows and NSWindowSharingNone on macOS) to stay hidden from capture tools.
  • Multi-channel audio: Separates your microphone from the meeting audio to track who is speaking.
  • BYO Key: Supports a wide range of AI providers including OpenAI, Anthropic, Gemini, and custom OpenAI-compatible endpoints.
  • Local Transcription: Offers an optional local speech-to-text mode using whisper.cpp for privacy and offline processing.
  • Meeting Memory: Automatically saves transcripts and generates summaries, key points, and action items after a session ends.

Related

  • Project
    jasoncheng7115/jt-live-whisper

    A comprehensive, 100% local AI toolkit for real-time speech transcription, translation, and meeting analysis that runs entirely on your own hardware to ensure privacy and zero cloud costs.

  • Project
    NanmiCoder/cc-haha

    cc‑haha is a cross‑platform desktop workbench (Electron + React) that lets you chat with Claude, ChatGPT, Grok and many other LLMs, manage multiple coding sessions, review diffs, preview web pages, generate images, run multi‑agent workflows, and even let agents control other desktop apps (Computer Use) – all from a single app.

  • Project
    katipally/openlive

    OpenLive is an open-source, local-first voice and vision layer that enables real-time, private interaction with AI models and coding agents without cloud-based audio fees.

  • Project
    moona3k/macparakeet

    MacParakeet is a free, open‑source macOS app (Apple‑Silicon only) that provides on‑device dictation, file/URL transcription, and meeting recording with local speech‑to‑text engines (Parakeet, Nemotron, WhisperKit, Cohere). It offers a UI for live transcription, library management, calendar‑aware auto‑recording, and optional cloud AI features (summaries, chat, text transforms). A companion CLI (`macparakeet-cli`) enables scriptable automation. Install via notarized DMG, Homebrew cask, or build from source.

  • Project
    theJayTea/WritingTools

    Writing Tools is a free, open‑source desktop app for Windows, Linux and macOS that lets you invoke an LLM anywhere on your computer with a hot‑key. It can proofread, rewrite, change tone, translate, summarise web pages or YouTube transcripts, and even chat with the model. You can use cloud APIs (Gemini, OpenAI, Anthropic, etc.) or run local models via Ollama, llama.cpp or Apple‑silicon MLX. The app is privacy‑focused (no telemetry, local storage of API keys) and licensed under GPL‑v3.