Local AI assistant that protects your data
Meetily is an open source meeting assistant that processes meeting recordings locally and does not require a cloud connection. Developed in Rust, the application offers fast voice transcription, speaker diarization and summarization capabilities with local language models.
Updates
- October 27, 2026: Stars 30,692 → 32,238, latest release v0.4.1 (September 12, 2026).
- September 13, 2026: Stars 29,473 → 30,692, latest release v0.4.1 (September 12, 2026).
- August 19, 2026: Stars 27,968 → 29,473, latest release v0.4.0 (June 5, 2026).
- August 2, 2026: Stars 15,565 → 27,968, latest release v0.4.0 (June 5, 2026).
What you get
- All audio transcription and summarization takes place on your device.
- It does not require a cloud connection, your data does not leave your computer.
- It works with local models like Ollama or your own endpoints.
Installation
git clone https://github.com/Zackriya-Solutions/meeting-minutes
cd meeting-minutes/frontend
pnpm install
./build-gpu.shIf you don't write code
By using this tool that locally processes my meeting recordings, I want to convert my audio transcripts into text and extract summaries from these texts in a way that protects my privacy. How can I create the most efficient meeting notes with local models, while ensuring my data doesn't leave my device?
Repository: https://github.com/Zackriya-Solutions/meetily. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-07-05: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.