Zackriya-Solutions/meetily

Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper live transcription, speaker diarization, and Ollama summarization built on Rust. 100% local processing. no cloud required. Meetily (Meetly Ai - https://meetily.ai) is the #1 Self-hosted, Open-source Ai meeting note taker for macOS & Windows. Understand How to write meeting minutes

What it solves

Meetily is designed for professionals and enterprises that need to transcribe and summarize meetings without compromising data privacy. It eliminates the risk of data breaches and compliance issues associated with cloud-based AI tools by ensuring that sensitive conversations never leave the user's local infrastructure.

How it works

The application captures microphone and system audio simultaneously and uses local AI models (such as Whisper or Parakeet) for real-time transcription. For summaries, it allows users to connect to local LLM providers like Ollama or external APIs (Claude, Groq, OpenRouter, or OpenAI-compatible endpoints). It is built as a self-contained app using a Rust-based backend (Tauri) and a Next.js frontend.

Who it’s for

It is intended for defense consultants, legal professionals, healthcare providers, and enterprise executives who handle sensitive information and require complete data sovereignty.

Highlights

  • Local-First Processing: All transcription and storage happen on the user's machine.
  • Real-time Transcription: Generates live transcripts as meetings progress.
  • Flexible AI Integration: Supports local LLMs via Ollama as well as various cloud providers.
  • GPU Acceleration: Utilizes Metal, CoreML, Vulkan, and CUDA (via source build) to speed up processing.
  • Multi-Platform Support: Compatible with macOS, Windows, and Linux.

Related

  • Project
    pretyflaco/millet

    Millet is an offline‑first Python tool that records dual‑channel audio from any meeting app, transcribes it with WhisperX (or MLX Whisper), diarises speakers via pyannote‑audio, and generates AI‑written summaries and professional PDFs. It offers three summarisation presets—high‑quality (cloud), confidential (TEE‑protected GLM‑5.3), and alternative (Kimi)—and supports multilingual transcription, voice‑print speaker recognition, structured markdown/YAML front‑matter, and optional Git sync. Linux is required for audio capture; macOS can run only the post‑capture steps.

  • Project
    stenolabs/stenoai

    A privacy-first, on-device AI notepad that records, transcribes, and summarizes confidential meetings using local AI models.

  • Project
    jasoncheng7115/jt-live-whisper

    A fully local AI toolkit for real-time speech transcription, translation, and meeting summarization that works across any system audio source without cloud APIs.

  • Project
    Muesli-HQ/muesli

    Muesli is a native macOS app that provides on‑device speech‑to‑text dictation and meeting transcription. It uses Apple‑silicon‑optimized models (Parakeet, Whisper, Nemotron, etc.) for low‑latency transcription, with optional hosted ASR via OpenAI/OpenRouter. Features include hold‑to‑talk dictation, voice‑driven editing (Quill), VAD‑driven chunking, speaker diarization, AI‑generated meeting notes, iCloud text sync, Siri/Shortcuts integration, and a JSON‑first CLI for agent automation.

  • Project
    fastrepl/anarlog

    A privacy-first, local-first AI meeting notepad that records audio directly from your device to provide transcriptions and summaries without needing a bot to join the call.